llama.cpp: all versions and old releases

metal : add Q2_0 support (#25419)
macOS/iOS:
- macOS Apple Silicon (arm64)
- macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED
- macOS Intel (x64)
- iOS XCFramework
Linux:
- Ubuntu x64 (CPU)
- Ubuntu arm64 (CPU)
- Ubuntu s390x (CPU)
- Ubuntu x64 (Vulkan)
- Ubuntu arm64 (Vulkan)
- Ubuntu x64 (ROCm 7.2)
- Ubuntu x64 (OpenVINO)
- Ubuntu x64 (SYCL FP32)
- Ubuntu x64 (SYCL FP16)
Android:
- Android arm64 (CPU)
Windows:
- Windows x64 (CPU)
- Windows arm64 (CPU)
- Windows arm64 (OpenCL Adreno)
- Windows x64 (CUDA 12) - CUDA 12.4 DLLs
- Windows x64 (CUDA 13) - CUDA 13.3 DLLs
- Windows x64 (Vulkan)
- Windows x64 (OpenVINO)
- Windows x64 (SYCL)
- Windows x64 (HIP)
openEuler:
- DISABLED
- openEuler x86 (310p)
- openEuler x86 (910b, ACL Graph)
- openEuler aarch64 (310p)
- openEuler aarch64 (910b, ACL Graph)
UI:
- UI

server: honour per-request reasoning_budget_tokens in chat completions (#23116)
- server: honour per-request reasoning_budget_tokens in chat completions
The reasoning-budget block in oaicompat_chat_params_parse read only the
server-level default (opt.reasoning_budget, typically -1) and the
Anthropic-style alias thinking_budget_tokens, but never the canonical
reasoning_budget_tokens field from the request body. Because the key
was then written into llama_params before the generic body-copy loop
ran, the copy loop found the key already present and silently skipped
the caller-supplied value. Any per-request override (e.g. 0 to
suppress thinking entirely) was therefore discarded.
Fix: read reasoning_budget_tokens from the request body first, so the
value that reaches the sampling layer is the one the caller intended.
Add a unit test in test-chat.cpp that exercises this path via
oaicompat_chat_params_parse with a Qwen3 template (which the autoparser
detects as a thinking-capable model) and asserts the returned
llama_params carries reasoning_budget_tokens == 0.
- server: honour per-request reasoning_budget_message in chat completions
The reasoning-budget block in oaicompat_chat_params_parse wrote
reasoning_budget_message into llama_params straight from the server-level
default (opt.reasoning_budget_message) and never read the canonical
reasoning_budget_message field from the request body. Because the key
was written before the generic body-copy loop ran, that loop found the
key already present and silently skipped the caller-supplied value. Any
per-request override of the message injected before the end tag when the
budget is exhausted was therefore discarded, even though server-task.cpp
already reads reasoning_budget_message from that data.
This mirrors the reasoning_budget_tokens bug fixed in the previous commit.
Fix: read reasoning_budget_message from the request body first, falling
back to the server default, so the value that reaches the sampling layer
is the one the caller intended.
While here, collapse the adjacent reasoning_budget_tokens override to a
single json_value() call; json_value already falls back to the default on
a missing/null/wrong-type key, so the explicit body.contains() guard was
redundant. No behavioral change.
Add a unit test in test-chat.cpp that exercises this path via
oaicompat_chat_params_parse with a Qwen3 template (which the autoparser
detects as a thinking-capable model) and asserts the returned
llama_params carries the per-request reasoning_budget_message rather than
the server default.
- cleanup
Co-authored-by: Xuan Son Nguyen son@huggingface.co
macOS/iOS:
- macOS Apple Silicon (arm64)
- macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED
- macOS Intel (x64)
- iOS XCFramework
Linux:
- Ubuntu x64 (CPU)
- Ubuntu arm64 (CPU)
- Ubuntu s390x (CPU)
- Ubuntu x64 (Vulkan)
- Ubuntu arm64 (Vulkan)
- Ubuntu x64 (ROCm 7.2)
- Ubuntu x64 (OpenVINO)
- Ubuntu x64 (SYCL FP32)
- Ubuntu x64 (SYCL FP16)
Android:
- Android arm64 (CPU)
Windows:
- Windows x64 (CPU)
- Windows arm64 (CPU)
- Windows arm64 (OpenCL Adreno)
- Windows x64 (CUDA 12) - CUDA 12.4 DLLs
- Windows x64 (CUDA 13) - CUDA 13.3 DLLs
- Windows x64 (Vulkan)
- Windows x64 (OpenVINO)
- Windows x64 (SYCL)
- Windows x64 (HIP)
openEuler:
- DISABLED
- openEuler x86 (310p)
- openEuler x86 (910b, ACL Graph)
- openEuler aarch64 (310p)
- openEuler aarch64 (910b, ACL Graph)
UI:
- UI

Vulkan: route large matmuls to medium tile on Adreno (#24877)
- [Vulkan] Fixes llama-cli breaking over longer promts sizes
The llama-cli was breaking for longer promts sizes for q4_0 quantized networks. Causing due to insufficient shared memory.
- Removed the un-used Adreno device
- Updated matmul for small pipeline.
macOS/iOS:
- macOS Apple Silicon (arm64)
- macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED
- macOS Intel (x64)
- iOS XCFramework
Linux:
- Ubuntu x64 (CPU)
- Ubuntu arm64 (CPU)
- Ubuntu s390x (CPU)
- Ubuntu x64 (Vulkan)
- Ubuntu arm64 (Vulkan)
- Ubuntu x64 (ROCm 7.2)
- Ubuntu x64 (OpenVINO)
- Ubuntu x64 (SYCL FP32)
- Ubuntu x64 (SYCL FP16)
Android:
- Android arm64 (CPU)
Windows:
- Windows x64 (CPU)
- Windows arm64 (CPU)
- Windows arm64 (OpenCL Adreno)
- Windows x64 (CUDA 12) - CUDA 12.4 DLLs
- Windows x64 (CUDA 13) - CUDA 13.3 DLLs
- Windows x64 (Vulkan)
- Windows x64 (OpenVINO)
- Windows x64 (SYCL)
- Windows x64 (HIP)
openEuler:
- DISABLED
- openEuler x86 (310p)
- openEuler x86 (910b, ACL Graph)
- openEuler aarch64 (310p)
- openEuler aarch64 (910b, ACL Graph)
UI:
- UI

server: improve tools, remove apply_diff (#25498)
- server: improve tools, remove apply_diff
- improve edit tool
- add tools_io abstraction
- add tools_io_basic
- fix build
- move utils to class member
- add const
macOS/iOS:
- macOS Apple Silicon (arm64)
- macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED
- macOS Intel (x64)
- iOS XCFramework
Linux:
- Ubuntu x64 (CPU)
- Ubuntu arm64 (CPU)
- Ubuntu s390x (CPU)
- Ubuntu x64 (Vulkan)
- Ubuntu arm64 (Vulkan)
- Ubuntu x64 (ROCm 7.2)
- Ubuntu x64 (OpenVINO)
- Ubuntu x64 (SYCL FP32)
- Ubuntu x64 (SYCL FP16)
Android:
- Android arm64 (CPU)
Windows:
- Windows x64 (CPU)
- Windows arm64 (CPU)
- Windows arm64 (OpenCL Adreno)
- Windows x64 (CUDA 12) - CUDA 12.4 DLLs
- Windows x64 (CUDA 13) - CUDA 13.3 DLLs
- Windows x64 (Vulkan)
- Windows x64 (OpenVINO)
- Windows x64 (SYCL)
- Windows x64 (HIP)
openEuler:
- DISABLED
- openEuler x86 (310p)
- openEuler x86 (910b, ACL Graph)
- openEuler aarch64 (310p)
- openEuler aarch64 (910b, ACL Graph)
UI:
- UI

cli: add --output option (#25484)
macOS/iOS:
- macOS Apple Silicon (arm64)
- macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED
- macOS Intel (x64)
- iOS XCFramework
Linux:
- Ubuntu x64 (CPU)
- Ubuntu arm64 (CPU)
- Ubuntu s390x (CPU)
- Ubuntu x64 (Vulkan)
- Ubuntu arm64 (Vulkan)
- Ubuntu x64 (ROCm 7.2)
- Ubuntu x64 (OpenVINO)
- Ubuntu x64 (SYCL FP32)
- Ubuntu x64 (SYCL FP16)
Android:
- Android arm64 (CPU)
Windows:
- Windows x64 (CPU)
- Windows arm64 (CPU)
- Windows arm64 (OpenCL Adreno)
- Windows x64 (CUDA 12) - CUDA 12.4 DLLs
- Windows x64 (CUDA 13) - CUDA 13.3 DLLs
- Windows x64 (Vulkan)
- Windows x64 (OpenVINO)
- Windows x64 (SYCL)
- Windows x64 (HIP)
openEuler:
- DISABLED
- openEuler x86 (310p)
- openEuler x86 (910b, ACL Graph)
- openEuler aarch64 (310p)
- openEuler aarch64 (910b, ACL Graph)
UI:
- UI

hexagon: add VISION RoPE support (#25216)
- hexagon: add VISION RoPE support
- hexagon: support RoPE on strided half-dim views for all modes
- hex-rope: decouple src0 DMA copy size from row stride
- hex-rope: support non-contiguous dst for RoPE
- hex-rope: fix dst spad pitch for non-contiguous dst
macOS/iOS:
- macOS Apple Silicon (arm64)
- macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED
- macOS Intel (x64)
- iOS XCFramework
Linux:
- Ubuntu x64 (CPU)
- Ubuntu arm64 (CPU)
- Ubuntu s390x (CPU)
- Ubuntu x64 (Vulkan)
- Ubuntu arm64 (Vulkan)
- Ubuntu x64 (ROCm 7.2)
- Ubuntu x64 (OpenVINO)
- Ubuntu x64 (SYCL FP32)
- Ubuntu x64 (SYCL FP16)
Android:
- Android arm64 (CPU)
Windows:
- Windows x64 (CPU)
- Windows arm64 (CPU)
- Windows arm64 (OpenCL Adreno)
- Windows x64 (CUDA 12) - CUDA 12.4 DLLs
- Windows x64 (CUDA 13) - CUDA 13.3 DLLs
- Windows x64 (Vulkan)
- Windows x64 (OpenVINO)
- Windows x64 (SYCL)
- Windows x64 (HIP)
openEuler:
- DISABLED
- openEuler x86 (310p)
- openEuler x86 (910b, ACL Graph)
- openEuler aarch64 (310p)
- openEuler aarch64 (910b, ACL Graph)
UI:
- UI

server : fix draft model fit vs load inconsistency (#25056)
- fix: draft model fit vs load inconsistency
- refactor(server): unify draft/mtp parameter initialization, model, and context load
- moves speculative init to speculative.cpp
- changes server_context_impl model_dft and ctx_dft to use raw pointers
- fix: don't throttle progress callback when loading draft model
- refactor: rename draft model/ctx load method
- fix: valign
macOS/iOS:
- macOS Apple Silicon (arm64)
- macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED
- macOS Intel (x64)
- iOS XCFramework
Linux:
- Ubuntu x64 (CPU)
- Ubuntu arm64 (CPU)
- Ubuntu s390x (CPU)
- Ubuntu x64 (Vulkan)
- Ubuntu arm64 (Vulkan)
- Ubuntu x64 (ROCm 7.2)
- Ubuntu x64 (OpenVINO)
- Ubuntu x64 (SYCL FP32)
- Ubuntu x64 (SYCL FP16)
Android:
- Android arm64 (CPU)
Windows:
- Windows x64 (CPU)
- Windows arm64 (CPU)
- Windows arm64 (OpenCL Adreno)
- Windows x64 (CUDA 12) - CUDA 12.4 DLLs
- Windows x64 (CUDA 13) - CUDA 13.3 DLLs
- Windows x64 (Vulkan)
- Windows x64 (OpenVINO)
- Windows x64 (SYCL)
- Windows x64 (HIP)
openEuler:
- DISABLED
- openEuler x86 (310p)
- openEuler x86 (910b, ACL Graph)
- openEuler aarch64 (310p)
- openEuler aarch64 (910b, ACL Graph)
UI:
- UI

opencl: general flash attention decode performance optimizations (#25366)
- opencl: vec flash-attention decode kernels for f16/q8_0/q4_0 KV
- opencl: improve non FA KQ mv kernels
- opencl: tweaks for multiquery FA
- opencl: some tweaks for FA q1 kernels
- opencl: FA with DK=DV=512 for gemma-4
- opencl: various fixes
- opencl: cleanup
- opencl: fix FA decode crash for DK=512 (gemma-4)
The DK=512 decode-only program does not create the f32_f16 prefill
kernel, so the compiled check in ensure_fa_variant never hit and
supports_op gave inconsistent answers for the same op. block_n is also
unset for DK=512 decode; guard it to avoid an out-of-range read at
dispatch.
- opencl: run DK=512 FA decode on CPU
DK=512 decode is bandwidth-bound and faster on the CPU than the GPU,
increasingly so with depth. Decline it in supports_op; prefill stays on the GPU.
- opencl: compile MQ_GQA=8 FA kernels in a minimal program
The full program compiled with -D MQ_GQA=8 runs the Adreno compiler out
of memory at DK>=256. Only the vec_mq kernels are used from this
program, so compile it with FA_MQ_ONLY, which excludes everything else.
Also include the program name in the compile error log.
- opencl: remove stray token in flash_attn_f32_f16.cl
A stray "." broke the f32_f16 program build.
- opencl: split f16-KV FA decode finer (FD_KV_PER_SPLIT_F16)
The 2048 default under-fills the GPU on single-query f16-KV decode;
use 512 for f16 KV to get more splits. Quantized KV keeps 2048.
Co-authored-by: Li He lih@qti.qualcomm.com
macOS/iOS:
- macOS Apple Silicon (arm64)
- macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED
- macOS Intel (x64)
- iOS XCFramework
Linux:
- Ubuntu x64 (CPU)
- Ubuntu arm64 (CPU)
- Ubuntu s390x (CPU)
- Ubuntu x64 (Vulkan)
- Ubuntu arm64 (Vulkan)
- Ubuntu x64 (ROCm 7.2)
- Ubuntu x64 (OpenVINO)
- Ubuntu x64 (SYCL FP32)
- Ubuntu x64 (SYCL FP16)
Android:
- Android arm64 (CPU)
Windows:
- Windows x64 (CPU)
- Windows arm64 (CPU)
- Windows arm64 (OpenCL Adreno)
- Windows x64 (CUDA 12) - CUDA 12.4 DLLs
- Windows x64 (CUDA 13) - CUDA 13.3 DLLs
- Windows x64 (Vulkan)
- Windows x64 (OpenVINO)
- Windows x64 (SYCL)
- Windows x64 (HIP)
openEuler:
- DISABLED
- openEuler x86 (310p)
- openEuler x86 (910b, ACL Graph)
- openEuler aarch64 (310p)
- openEuler aarch64 (910b, ACL Graph)
UI:
- UI

Fix stale tensor-split params for draft models (#24814)
- meta: fix tensor split metadata for GQA attention
- Tidied the code a bit to match existing style
- Revert "Tidied the code a bit to match existing style"
This reverts commit b90c6c6.
- Reverted the ggml-backend-meta asset hack.
macOS/iOS:
- macOS Apple Silicon (arm64)
- macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED
- macOS Intel (x64)
- iOS XCFramework
Linux:
- Ubuntu x64 (CPU)
- Ubuntu arm64 (CPU)
- Ubuntu s390x (CPU)
- Ubuntu x64 (Vulkan)
- Ubuntu arm64 (Vulkan)
- Ubuntu x64 (ROCm 7.2)
- Ubuntu x64 (OpenVINO)
- Ubuntu x64 (SYCL FP32)
- Ubuntu x64 (SYCL FP16)
Android:
- Android arm64 (CPU)
Windows:
- Windows x64 (CPU)
- Windows arm64 (CPU)
- Windows arm64 (OpenCL Adreno)
- Windows x64 (CUDA 12) - CUDA 12.4 DLLs
- Windows x64 (CUDA 13) - CUDA 13.3 DLLs
- Windows x64 (Vulkan)
- Windows x64 (OpenVINO)
- Windows x64 (SYCL)
- Windows x64 (HIP)
openEuler:
- DISABLED
- openEuler x86 (310p)
- openEuler x86 (910b, ACL Graph)
- openEuler aarch64 (310p)
- openEuler aarch64 (910b, ACL Graph)
UI:
- UI

llama : add guard for K/V rotation input when buffer is unallocated (#25215)
llm_graph_input_attn_kv::set_input and llm_graph_input_attn_kv_iswa::set_input
call set_input_k_rot / set_input_v_rot whenever the rotation tensor pointer is
non-null, but the tensor's buffer can be unallocated (NULL) when a graph only
stores K/V without attending -- e.g. DFlash speculative decoding's KV-injection
pass. set_input_k_rot then calls ggml_backend_buffer_is_host() on a NULL buffer
and aborts with GGML_ASSERT(buffer).
Guard the four k_rot/v_rot inputs with the same "&& ->buffer" check that the
adjacent kq_mask inputs already use in these two functions. When the buffer is
unallocated there is no data to upload, so skipping is correct.
Fixes #25191
Signed-off-by: liminfei-amd 91481003+liminfei-amd@users.noreply.github.com
macOS/iOS:
- macOS Apple Silicon (arm64)
- macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED
- macOS Intel (x64)
- iOS XCFramework
Linux:
- Ubuntu x64 (CPU)
- Ubuntu arm64 (CPU)
- Ubuntu s390x (CPU)
- Ubuntu x64 (Vulkan)
- Ubuntu arm64 (Vulkan)
- Ubuntu x64 (ROCm 7.2)
- Ubuntu x64 (OpenVINO)
- Ubuntu x64 (SYCL FP32)
- Ubuntu x64 (SYCL FP16)
Android:
- Android arm64 (CPU)
Windows:
- Windows x64 (CPU)
- Windows arm64 (CPU)
- Windows arm64 (OpenCL Adreno)
- Windows x64 (CUDA 12) - CUDA 12.4 DLLs
- Windows x64 (CUDA 13) - CUDA 13.3 DLLs
- Windows x64 (Vulkan)
- Windows x64 (OpenVINO)
- Windows x64 (SYCL)
- Windows x64 (HIP)
openEuler:
- DISABLED
- openEuler x86 (310p)
- openEuler x86 (910b, ACL Graph)
- openEuler aarch64 (310p)
- openEuler aarch64 (910b, ACL Graph)
UI:
- UI

chat: trim messages sent to StepFun parser (fixes long reasoning loops) (#25238)
- chat: trim messages sent to StepFun parser (fixes long reasoning loops)
- add regression test; remove duplicate template
- chat: trim StepFun content parts before rendering
The StepFun trim workaround ran on the already-rendered messages, where
typed content parts have been concatenated into a single string, so the
per-part whitespace could no longer be reached. Move the trim ahead of
rendering and apply it to content_parts text as well as the string
content and reasoning_content. Adds a content-parts regression test.
Co-Authored-By: Piotr Wilkin ilintar@gmail.com
Assisted-By: Claude Fable 5 noreply@anthropic.com
Co-authored-by: tarruda tpadilha84@gmail.com
macOS/iOS:
- macOS Apple Silicon (arm64)
- macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED
- macOS Intel (x64)
- iOS XCFramework
Linux:
- Ubuntu x64 (CPU)
- Ubuntu arm64 (CPU)
- Ubuntu s390x (CPU)
- Ubuntu x64 (Vulkan)
- Ubuntu arm64 (Vulkan)
- Ubuntu x64 (ROCm 7.2)
- Ubuntu x64 (OpenVINO)
- Ubuntu x64 (SYCL FP32)
- Ubuntu x64 (SYCL FP16)
Android:
- Android arm64 (CPU)
Windows:
- Windows x64 (CPU)
- Windows arm64 (CPU)
- Windows arm64 (OpenCL Adreno)
- Windows x64 (CUDA 12) - CUDA 12.4 DLLs
- Windows x64 (CUDA 13) - CUDA 13.3 DLLs
- Windows x64 (Vulkan)
- Windows x64 (OpenVINO)
- Windows x64 (SYCL)
- Windows x64 (HIP)
openEuler:
- DISABLED
- openEuler x86 (310p)
- openEuler x86 (910b, ACL Graph)
- openEuler aarch64 (310p)
- openEuler aarch64 (910b, ACL Graph)
UI:
- UI

llama : add llama_model_ftype_name() (#25134)
- llama : add llama_model_ftype_name()
Expose the model file type (quantization) name, e.g. "Q8_0" or
"Q4_K - Medium", through a new public C API. The returned pointer is
valid for the lifetime of the model and nullptr when the model is
invalid or the file type is unknown.
Signed-off-by: Adrien Gallouët angt@huggingface.co
- Export enum
Signed-off-by: Adrien Gallouët angt@huggingface.co
- s/llama_model_ftype_name/llama_ftype_name/
Signed-off-by: Adrien Gallouët angt@huggingface.co
- Move "(guessed)" to the front in llama_ftype_name
Prepend the "(guessed)" label instead of appending it. This allows removing
the non-thread-safe static std::string, making the function allocation-free.
Signed-off-by: Adrien Gallouët angt@huggingface.co
- Add LLAMA_FTYPE_PREFIX
Signed-off-by: Adrien Gallouët angt@huggingface.co
- Dont check for model
Signed-off-by: Adrien Gallouët angt@huggingface.co
Signed-off-by: Adrien Gallouët angt@huggingface.co
macOS/iOS:
- macOS Apple Silicon (arm64)
- macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED
- macOS Intel (x64)
- iOS XCFramework
Linux:
- Ubuntu x64 (CPU)
- Ubuntu arm64 (CPU)
- Ubuntu s390x (CPU)
- Ubuntu x64 (Vulkan)
- Ubuntu arm64 (Vulkan)
- Ubuntu x64 (ROCm 7.2)
- Ubuntu x64 (OpenVINO)
- Ubuntu x64 (SYCL FP32)
- Ubuntu x64 (SYCL FP16)
Android:
- Android arm64 (CPU)
Windows:
- Windows x64 (CPU)
- Windows arm64 (CPU)
- Windows arm64 (OpenCL Adreno)
- Windows x64 (CUDA 12) - CUDA 12.4 DLLs
- Windows x64 (CUDA 13) - CUDA 13.3 DLLs
- Windows x64 (Vulkan)
- Windows x64 (OpenVINO)
- Windows x64 (SYCL)
- Windows x64 (HIP)
openEuler:
- DISABLED
- openEuler x86 (310p)
- openEuler x86 (910b, ACL Graph)
- openEuler aarch64 (310p)
- openEuler aarch64 (910b, ACL Graph)
UI:
- UI

opencl: allow loading precompiled binary kernels from library (#23042)
- opencl: allow loading binary kernel
- opencl: add libdl.h
- ggml-backend-dl is in ggml, which depends backend libs, thus
ggml-opencl cannot depend on ggml-backend-dl
- add libdl.h to break cyclic dep
- opencl: allow loading bin kernel lib
- opencl: load gemm_moe_mxfp4_f32_ns from kernel lib if available
- opencl: load q8_0 gemm from kernel lib
- opencl: load q4_0 moe gemm from kernel lib
- opencl: load q4_1 moe gemm from kernel lib
- opencl: load q4_k moe gemm from kernel lib
- opencl: always declare get_adreno_bin_kernel_func_t
- opencl: rephrase message
- opencl: fix for rebase
- opencl: update doc
macOS/iOS:
- macOS Apple Silicon (arm64)
- macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED
- macOS Intel (x64)
- iOS XCFramework
Linux:
- Ubuntu x64 (CPU)
- Ubuntu arm64 (CPU)
- Ubuntu s390x (CPU)
- Ubuntu x64 (Vulkan)
- Ubuntu arm64 (Vulkan)
- Ubuntu x64 (ROCm 7.2)
- Ubuntu x64 (OpenVINO)
- Ubuntu x64 (SYCL FP32)
- Ubuntu x64 (SYCL FP16)
Android:
- Android arm64 (CPU)
Windows:
- Windows x64 (CPU)
- Windows arm64 (CPU)
- Windows arm64 (OpenCL Adreno)
- Windows x64 (CUDA 12) - CUDA 12.4 DLLs
- Windows x64 (CUDA 13) - CUDA 13.3 DLLs
- Windows x64 (Vulkan)
- Windows x64 (OpenVINO)
- Windows x64 (SYCL)
- Windows x64 (HIP)
openEuler:
- DISABLED
- openEuler x86 (310p)
- openEuler x86 (910b, ACL Graph)
- openEuler aarch64 (310p)
- openEuler aarch64 (910b, ACL Graph)
UI:
- UI

opencl: initial q1_0 support (#25160)
- opencl: general q1_0 support
- opencl: add Adreno GEMM/GEMV for q1_0
macOS/iOS:
- macOS Apple Silicon (arm64)
- macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED
- macOS Intel (x64)
- iOS XCFramework
Linux:
- Ubuntu x64 (CPU)
- Ubuntu arm64 (CPU)
- Ubuntu s390x (CPU)
- Ubuntu x64 (Vulkan)
- Ubuntu arm64 (Vulkan)
- Ubuntu x64 (ROCm 7.2)
- Ubuntu x64 (OpenVINO)
- Ubuntu x64 (SYCL FP32)
- Ubuntu x64 (SYCL FP16)
Android:
- Android arm64 (CPU)
Windows:
- Windows x64 (CPU)
- Windows arm64 (CPU)
- Windows arm64 (OpenCL Adreno)
- Windows x64 (CUDA 12) - CUDA 12.4 DLLs
- Windows x64 (CUDA 13) - CUDA 13.3 DLLs
- Windows x64 (Vulkan)
- Windows x64 (OpenVINO)
- Windows x64 (SYCL)
- Windows x64 (HIP)
openEuler:
- DISABLED
- openEuler x86 (310p)
- openEuler x86 (910b, ACL Graph)
- openEuler aarch64 (310p)
- openEuler aarch64 (910b, ACL Graph)
UI:
- UI

Revert "sched : reintroduce less synchronizations during split compute (#20793)" (#25138)
macOS/iOS:
- macOS Apple Silicon (arm64)
- macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED
- macOS Intel (x64)
- iOS XCFramework
Linux:
- Ubuntu x64 (CPU)
- Ubuntu arm64 (CPU)
- Ubuntu s390x (CPU)
- Ubuntu x64 (Vulkan)
- Ubuntu arm64 (Vulkan)
- Ubuntu x64 (ROCm 7.2)
- Ubuntu x64 (OpenVINO)
- Ubuntu x64 (SYCL FP32)
- Ubuntu x64 (SYCL FP16)
Android:
- Android arm64 (CPU)
Windows:
- Windows x64 (CPU)
- Windows arm64 (CPU)
- Windows arm64 (OpenCL Adreno)
- Windows x64 (CUDA 12) - CUDA 12.4 DLLs
- Windows x64 (CUDA 13) - CUDA 13.3 DLLs
- Windows x64 (Vulkan)
- Windows x64 (OpenVINO)
- Windows x64 (SYCL)
- Windows x64 (HIP)
openEuler:
- DISABLED
- openEuler x86 (310p)
- openEuler x86 (910b, ACL Graph)
- openEuler aarch64 (310p)
- openEuler aarch64 (910b, ACL Graph)
UI:
- UI

jinja, chat: add --reasoning-preserve flag (#25105)
- jinja, chat: add --reasoning-preserve flag
- correct help message
macOS/iOS:
- macOS Apple Silicon (arm64)
- macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED
- macOS Intel (x64)
- iOS XCFramework
Linux:
- Ubuntu x64 (CPU)
- Ubuntu arm64 (CPU)
- Ubuntu s390x (CPU)
- Ubuntu x64 (Vulkan)
- Ubuntu arm64 (Vulkan)
- Ubuntu x64 (ROCm 7.2)
- Ubuntu x64 (OpenVINO)
- Ubuntu x64 (SYCL FP32)
- Ubuntu x64 (SYCL FP16)
Android:
- Android arm64 (CPU)
Windows:
- Windows x64 (CPU)
- Windows arm64 (CPU)
- Windows arm64 (OpenCL Adreno)
- Windows x64 (CUDA 12) - CUDA 12.4 DLLs
- Windows x64 (CUDA 13) - CUDA 13.3 DLLs
- Windows x64 (Vulkan)
- Windows x64 (OpenVINO)
- Windows x64 (SYCL)
- Windows x64 (HIP)
openEuler:
- DISABLED
- openEuler x86 (310p)
- openEuler x86 (910b, ACL Graph)
- openEuler aarch64 (310p)
- openEuler aarch64 (910b, ACL Graph)
UI:
- UI

opencl: flash attention improvement (#25069)
- opencl: rework FA kernel for f16 and f32
- opencl: flash-attention prefill prepass kernels
- flash_attn_kv_pad_f16 pads the tail KV tile to a BLOCK_N multiple
- flash_attn_mask_pad_f16 pads the matching mask tile
- flash_attn_blk_f16 classifies each KV tile per query block as
fully masked / mixed / fully unmasked, so
the main kernel can skip fully-masked tiles
and the mask lookup for fully-unmasked ones
- opencl: FA kernels for q4_0 and q8_0
- opencl: set_rows for f32 to q8_0/q4_0
- opencl: dequant kernels for q4_0 and q8_0
- opencl: add FA tile tuning table with override
- opencl: wire host side for FA
- opencl: q4_0 MoE tensors are also SOA'ed
- opencl: cosmetic fix
- opencl: refactor, also clarify some code paths in comments
- opencl: fix inifity for -cl-finite-math-only
Co-authored-by: Li He lih@qti.qualcomm.com
macOS/iOS:
- macOS Apple Silicon (arm64)
- macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED
- macOS Intel (x64)
- iOS XCFramework
Linux:
- Ubuntu x64 (CPU)
- Ubuntu arm64 (CPU)
- Ubuntu s390x (CPU)
- Ubuntu x64 (Vulkan)
- Ubuntu arm64 (Vulkan)
- Ubuntu x64 (ROCm 7.2)
- Ubuntu x64 (OpenVINO)
- Ubuntu x64 (SYCL FP32)
- Ubuntu x64 (SYCL FP16)
Android:
- Android arm64 (CPU)
Windows:
- Windows x64 (CPU)
- Windows arm64 (CPU)
- Windows arm64 (OpenCL Adreno)
- Windows x64 (CUDA 12) - CUDA 12.4 DLLs
- Windows x64 (CUDA 13) - CUDA 13.3 DLLs
- Windows x64 (Vulkan)
- Windows x64 (OpenVINO)
- Windows x64 (SYCL)
- Windows x64 (HIP)
openEuler:
- DISABLED
- openEuler x86 (310p)
- openEuler x86 (910b, ACL Graph)
- openEuler aarch64 (310p)
- openEuler aarch64 (910b, ACL Graph)
UI:
- UI

app : allow --version, --licenses & --help (#25054)
Signed-off-by: Adrien Gallouët angt@huggingface.co
macOS/iOS:
- macOS Apple Silicon (arm64)
- macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED
- macOS Intel (x64)
- iOS XCFramework
Linux:
- Ubuntu x64 (CPU)
- Ubuntu arm64 (CPU)
- Ubuntu s390x (CPU)
- Ubuntu x64 (Vulkan)
- Ubuntu arm64 (Vulkan)
- Ubuntu x64 (ROCm 7.2)
- Ubuntu x64 (OpenVINO)
- Ubuntu x64 (SYCL FP32)
- Ubuntu x64 (SYCL FP16)
Android:
- Android arm64 (CPU)
Windows:
- Windows x64 (CPU)
- Windows arm64 (CPU)
- Windows arm64 (OpenCL Adreno)
- Windows x64 (CUDA 12) - CUDA 12.4 DLLs
- Windows x64 (CUDA 13) - CUDA 13.3 DLLs
- Windows x64 (Vulkan)
- Windows x64 (OpenVINO)
- Windows x64 (SYCL)
- Windows x64 (HIP)
openEuler:
- DISABLED
- openEuler x86 (310p)
- openEuler x86 (910b, ACL Graph)
- openEuler aarch64 (310p)
- openEuler aarch64 (910b, ACL Graph)
UI:
- UI

opencl: flush profiling batch at shutdown for incomplete batches (#25016)
macOS/iOS:
- macOS Apple Silicon (arm64)
- macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED
- macOS Intel (x64)
- iOS XCFramework
Linux:
- Ubuntu x64 (CPU)
- Ubuntu arm64 (CPU)
- Ubuntu s390x (CPU)
- Ubuntu x64 (Vulkan)
- Ubuntu arm64 (Vulkan)
- Ubuntu x64 (ROCm 7.2)
- Ubuntu x64 (OpenVINO)
- Ubuntu x64 (SYCL FP32)
- Ubuntu x64 (SYCL FP16)
Android:
- Android arm64 (CPU)
Windows:
- Windows x64 (CPU)
- Windows arm64 (CPU)
- Windows arm64 (OpenCL Adreno)
- Windows x64 (CUDA 12) - CUDA 12.4 DLLs
- Windows x64 (CUDA 13) - CUDA 13.3 DLLs
- Windows x64 (Vulkan)
- Windows x64 (OpenVINO)
- Windows x64 (SYCL)
- Windows x64 (HIP)
openEuler:
- DISABLED
- openEuler x86 (310p)
- openEuler x86 (910b, ACL Graph)
- openEuler aarch64 (310p)
- openEuler aarch64 (910b, ACL Graph)
UI:
- UI

sycl : fix the failed UT cases of conv_3d (#24900)
macOS/iOS:
- macOS Apple Silicon (arm64)
- macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED
- macOS Intel (x64)
- iOS XCFramework
Linux:
- Ubuntu x64 (CPU)
- Ubuntu arm64 (CPU)
- Ubuntu s390x (CPU)
- Ubuntu x64 (Vulkan)
- Ubuntu arm64 (Vulkan)
- Ubuntu x64 (ROCm 7.2)
- Ubuntu x64 (OpenVINO)
- Ubuntu x64 (SYCL FP32)
- Ubuntu x64 (SYCL FP16)
Android:
- Android arm64 (CPU)
Windows:
- Windows x64 (CPU)
- Windows arm64 (CPU)
- Windows arm64 (OpenCL Adreno)
- Windows x64 (CUDA 12) - CUDA 12.4 DLLs
- Windows x64 (CUDA 13) - CUDA 13.3 DLLs
- Windows x64 (Vulkan)
- Windows x64 (OpenVINO)
- Windows x64 (SYCL)
- Windows x64 (HIP)
openEuler:
- DISABLED
- openEuler x86 (310p)
- openEuler x86 (910b, ACL Graph)
- openEuler aarch64 (310p)
- openEuler aarch64 (910b, ACL Graph)
UI:
- UI

vulkan: Apply bias before softmax in FA, to avoid overflow (#24909)
macOS/iOS:
- macOS Apple Silicon (arm64)
- macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED
- macOS Intel (x64)
- iOS XCFramework
Linux:
- Ubuntu x64 (CPU)
- Ubuntu arm64 (CPU)
- Ubuntu s390x (CPU)
- Ubuntu x64 (Vulkan)
- Ubuntu arm64 (Vulkan)
- Ubuntu x64 (ROCm 7.2)
- Ubuntu x64 (OpenVINO)
- Ubuntu x64 (SYCL FP32)
- Ubuntu x64 (SYCL FP16)
Android:
- Android arm64 (CPU)
Windows:
- Windows x64 (CPU)
- Windows arm64 (CPU)
- Windows arm64 (OpenCL Adreno)
- Windows x64 (CUDA 12) - CUDA 12.4 DLLs
- Windows x64 (CUDA 13) - CUDA 13.3 DLLs
- Windows x64 (Vulkan)
- Windows x64 (OpenVINO)
- Windows x64 (SYCL)
- Windows x64 (HIP)
openEuler:
- DISABLED
- openEuler x86 (310p)
- openEuler x86 (910b, ACL Graph)
- openEuler aarch64 (310p)
- openEuler aarch64 (910b, ACL Graph)
UI:
- UI

server : Add id to tool call responses api (#24882)
macOS/iOS:
- macOS Apple Silicon (arm64)
- macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED
- macOS Intel (x64)
- iOS XCFramework
Linux:
- Ubuntu x64 (CPU)
- Ubuntu arm64 (CPU)
- Ubuntu s390x (CPU)
- Ubuntu x64 (Vulkan)
- Ubuntu arm64 (Vulkan)
- Ubuntu x64 (ROCm 7.2)
- Ubuntu x64 (OpenVINO)
- Ubuntu x64 (SYCL FP32)
- Ubuntu x64 (SYCL FP16)
Android:
- Android arm64 (CPU)
Windows:
- Windows x64 (CPU)
- Windows arm64 (CPU)
- Windows arm64 (OpenCL Adreno)
- Windows x64 (CUDA 12) - CUDA 12.4 DLLs
- Windows x64 (CUDA 13) - CUDA 13.3 DLLs
- Windows x64 (Vulkan)
- Windows x64 (OpenVINO)
- Windows x64 (SYCL)
- Windows x64 (HIP)
openEuler:
- DISABLED
- openEuler x86 (310p)
- openEuler x86 (910b, ACL Graph)
- openEuler aarch64 (310p)
- openEuler aarch64 (910b, ACL Graph)
UI:
- UI

common/peg : implement ac parser for stricter grammar generation (#24869)
- common/peg : implement ac parser
- cont : extract functions
- cont : tidy up
- cont : remove a test
- cont : move ac() def
macOS/iOS:
- macOS Apple Silicon (arm64)
- macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED
- macOS Intel (x64)
- iOS XCFramework
Linux:
- Ubuntu x64 (CPU)
- Ubuntu arm64 (CPU)
- Ubuntu s390x (CPU)
- Ubuntu x64 (Vulkan)
- Ubuntu arm64 (Vulkan)
- Ubuntu x64 (ROCm 7.2)
- Ubuntu x64 (OpenVINO)
- Ubuntu x64 (SYCL FP32)
- Ubuntu x64 (SYCL FP16)
Android:
- Android arm64 (CPU)
Windows:
- Windows x64 (CPU)
- Windows arm64 (CPU)
- Windows arm64 (OpenCL Adreno)
- Windows x64 (CUDA 12) - CUDA 12.4 DLLs
- Windows x64 (CUDA 13) - CUDA 13.3 DLLs
- Windows x64 (Vulkan)
- Windows x64 (OpenVINO)
- Windows x64 (SYCL)
- Windows x64 (HIP)
openEuler:
- DISABLED
- openEuler x86 (310p)
- openEuler x86 (910b, ACL Graph)
- openEuler aarch64 (310p)
- openEuler aarch64 (910b, ACL Graph)
UI:
- UI

common/peg : refactor until gbnf grammar generation (#24839)
- common/peg : refactor until gbnf grammar into an ac automaton
- cont : add a test with multiple strings
- cont : pad state with 0s so rules line up
- cont : clean up comments
- cont : use set everywhere
- cont : inline state num string padding
- cont : add a ref to PR
- cont : fix regression in server-tools.cpp
macOS/iOS:
- macOS Apple Silicon (arm64)
- macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED
- macOS Intel (x64)
- iOS XCFramework
Linux:
- Ubuntu x64 (CPU)
- Ubuntu arm64 (CPU)
- Ubuntu s390x (CPU)
- Ubuntu x64 (Vulkan)
- Ubuntu arm64 (Vulkan)
- Ubuntu x64 (ROCm 7.2)
- Ubuntu x64 (OpenVINO)
- Ubuntu x64 (SYCL FP32)
- Ubuntu x64 (SYCL FP16)
Android:
- Android arm64 (CPU)
Windows:
- Windows x64 (CPU)
- Windows arm64 (CPU)
- Windows arm64 (OpenCL Adreno)
- Windows x64 (CUDA 12) - CUDA 12.4 DLLs
- Windows x64 (CUDA 13) - CUDA 13.3 DLLs
- Windows x64 (Vulkan)
- Windows x64 (OpenVINO)
- Windows x64 (SYCL)
- Windows x64 (HIP)
openEuler:
- DISABLED
- openEuler x86 (310p)
- openEuler x86 (910b, ACL Graph)
- openEuler aarch64 (310p)
- openEuler aarch64 (910b, ACL Graph)
UI:
- UI

ggml-webgpu: add adapter toggles for F16 on Vulkan + NVIDIA
macOS/iOS:
- macOS Apple Silicon (arm64)
- macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED
- macOS Intel (x64)
- iOS XCFramework
Linux:
- Ubuntu x64 (CPU)
- Ubuntu arm64 (CPU)
- Ubuntu s390x (CPU)
- Ubuntu x64 (Vulkan)
- Ubuntu arm64 (Vulkan)
- Ubuntu x64 (ROCm 7.2)
- Ubuntu x64 (OpenVINO)
- Ubuntu x64 (SYCL FP32)
- Ubuntu x64 (SYCL FP16)
Android:
- Android arm64 (CPU)
Windows:
- Windows x64 (CPU)
- Windows arm64 (CPU)
- Windows x64 (CUDA 12) - CUDA 12.4 DLLs
- Windows x64 (CUDA 13) - CUDA 13.3 DLLs
- Windows x64 (Vulkan)
- Windows x64 (OpenVINO)
- Windows x64 (SYCL)
- Windows x64 (HIP)
openEuler:
- DISABLED
- openEuler x86 (310p)
- openEuler x86 (910b, ACL Graph)
- openEuler aarch64 (310p)
- openEuler aarch64 (910b, ACL Graph)
UI:
- UI

ggml-cpu: support K tails in power10 Q8/Q4 MMA matmul (#24753)
- ggml-cpu: support K tails in Power10 MMA Q8/Q4 matmul
This patch removes the requirement that K be divisible by kc in the tinyBlas_Q0_PPC tiled matmul path. Process the final K panel using its actual depth and pass the reduced panel size through packing and kernel execution. This allows more workloads to use the MMA kernel and reduces fallback to mnpack.
- Apply suggestion from @taronaeo
Co-authored-by: Aaron Teo taronaeo@gmail.com
Co-authored-by: Aaron Teo taronaeo@gmail.com
macOS/iOS:
- macOS Apple Silicon (arm64)
- macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED
- macOS Intel (x64)
- iOS XCFramework
Linux:
- Ubuntu x64 (CPU)
- Ubuntu arm64 (CPU)
- Ubuntu s390x (CPU)
- Ubuntu x64 (Vulkan)
- Ubuntu arm64 (Vulkan)
- Ubuntu x64 (ROCm 7.2)
- Ubuntu x64 (OpenVINO)
- Ubuntu x64 (SYCL FP32)
- Ubuntu x64 (SYCL FP16)
Android:
- Android arm64 (CPU)
Windows:
- Windows x64 (CPU)
- Windows arm64 (CPU)
- Windows x64 (CUDA 12) - CUDA 12.4 DLLs
- Windows x64 (CUDA 13) - CUDA 13.3 DLLs
- Windows x64 (Vulkan)
- Windows x64 (OpenVINO)
- Windows x64 (SYCL)
- Windows x64 (HIP)
openEuler:
- DISABLED
- openEuler x86 (310p)
- openEuler x86 (910b, ACL Graph)
- openEuler aarch64 (310p)
- openEuler aarch64 (910b, ACL Graph)
UI:
- UI

metal : check for BF16 support in concat kernel (#24747)
macOS/iOS:
- macOS Apple Silicon (arm64)
- macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED
- macOS Intel (x64)
- iOS XCFramework
Linux:
- Ubuntu x64 (CPU)
- Ubuntu arm64 (CPU)
- Ubuntu s390x (CPU)
- Ubuntu x64 (Vulkan)
- Ubuntu arm64 (Vulkan)
- Ubuntu x64 (ROCm 7.2)
- Ubuntu x64 (OpenVINO)
- Ubuntu x64 (SYCL FP32)
- Ubuntu x64 (SYCL FP16)
Android:
- Android arm64 (CPU)
Windows:
- Windows x64 (CPU)
- Windows arm64 (CPU)
- Windows x64 (CUDA 12) - CUDA 12.4 DLLs
- Windows x64 (CUDA 13) - CUDA 13.3 DLLs
- Windows x64 (Vulkan)
- Windows x64 (OpenVINO)
- Windows x64 (SYCL)
- Windows x64 (HIP)
openEuler:
- DISABLED
- openEuler x86 (310p)
- openEuler x86 (910b, ACL Graph)
- openEuler aarch64 (310p)
- openEuler aarch64 (910b, ACL Graph)
UI:
- UI

sycl: Add optional USM system allocations (#22526)
This introduces an optional feature to allocate large GPU buffers (≥ 1GB)
using USM system allocations if supported by the device. It allows using
buffers from the system allocator then letting the system manage memory
migrations between host and device as necessary.
This feature is disabled by default and requires the GGML_SYCL_USM_SYSTEM
environment variable to enable. If USM system allocations are not supported
by the device or the system, we fallback to regular allocations.
This feature can allow VRAM overcommit. For example, the test below fails
on B580 due to lack of memory for allocation, but it passes when enabling
USM system allocations:
./examples/sycl/test.sh -m Qwen3.5-27B-Q3_K_M.gguf -lv 4
Signed-off-by: Francois Dugast francois.dugast@intel.com
macOS/iOS:
- macOS Apple Silicon (arm64)
- macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED
- macOS Intel (x64)
- iOS XCFramework
Linux:
- Ubuntu x64 (CPU)
- Ubuntu arm64 (CPU)
- Ubuntu s390x (CPU)
- Ubuntu x64 (Vulkan)
- Ubuntu arm64 (Vulkan)
- Ubuntu x64 (ROCm 7.2)
- Ubuntu x64 (OpenVINO)
- Ubuntu x64 (SYCL FP32)
- Ubuntu x64 (SYCL FP16)
Android:
- Android arm64 (CPU)
Windows:
- Windows x64 (CPU)
- Windows arm64 (CPU)
- Windows x64 (CUDA 12) - CUDA 12.4 DLLs
- Windows x64 (CUDA 13) - CUDA 13.3 DLLs
- Windows x64 (Vulkan)
- Windows x64 (SYCL)
- Windows x64 (HIP)
openEuler:
- DISABLED
- openEuler x86 (310p)
- openEuler x86 (910b, ACL Graph)
- openEuler aarch64 (310p)
- openEuler aarch64 (910b, ACL Graph)
UI:
- UI

chat: add dedicated Cohere2MoE (North Code) parser (#24615)
- chat: add dedicated Cohere2MoE (North Code) parser
- Some renames to make @CISC happy :>
macOS/iOS:
- macOS Apple Silicon (arm64)
- macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED
- macOS Intel (x64)
- iOS XCFramework
Linux:
- Ubuntu x64 (CPU)
- Ubuntu arm64 (CPU)
- Ubuntu s390x (CPU)
- Ubuntu x64 (Vulkan)
- Ubuntu arm64 (Vulkan)
- Ubuntu x64 (ROCm 7.2)
- Ubuntu x64 (OpenVINO)
- Ubuntu x64 (SYCL FP32)
- Ubuntu x64 (SYCL FP16)
Android:
- Android arm64 (CPU)
Windows:
- Windows x64 (CPU)
- Windows arm64 (CPU)
- Windows x64 (CUDA 12) - CUDA 12.4 DLLs
- Windows x64 (CUDA 13) - CUDA 13.3 DLLs
- Windows x64 (Vulkan)
- Windows x64 (SYCL)
- Windows x64 (HIP)
openEuler:
- DISABLED
- openEuler x86 (310p)
- openEuler x86 (910b, ACL Graph)
- openEuler aarch64 (310p)
- openEuler aarch64 (910b, ACL Graph)
UI:
- UI

add sycl to check-release (#24583)
macOS/iOS:
- macOS Apple Silicon (arm64)
- macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED
- macOS Intel (x64)
- iOS XCFramework
Linux:
- Ubuntu x64 (CPU)
- Ubuntu arm64 (CPU)
- Ubuntu s390x (CPU)
- Ubuntu x64 (Vulkan)
- Ubuntu arm64 (Vulkan)
- Ubuntu x64 (ROCm 7.2)
- Ubuntu x64 (OpenVINO)
- Ubuntu x64 (SYCL FP32)
- Ubuntu x64 (SYCL FP16)
Android:
- Android arm64 (CPU)
Windows:
- Windows x64 (CPU)
- Windows arm64 (CPU)
- Windows x64 (CUDA 12) - CUDA 12.4 DLLs
- Windows x64 (CUDA 13) - CUDA 13.3 DLLs
- Windows x64 (Vulkan)
- Windows x64 (SYCL)
- Windows x64 (HIP)
openEuler:
- DISABLED
- openEuler x86 (310p)
- openEuler x86 (910b, ACL Graph)
- openEuler aarch64 (310p)
- openEuler aarch64 (910b, ACL Graph)
UI:
- UI

ci : unbreak release harder (#24545)
- unbreak release harder
- missed one
- remove missing test for now
macOS/iOS:
- macOS Apple Silicon (arm64)
- macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED
- macOS Intel (x64)
- iOS XCFramework
Linux:
- Ubuntu x64 (CPU)
- Ubuntu arm64 (CPU)
- Ubuntu s390x (CPU)
- Ubuntu x64 (Vulkan)
- Ubuntu arm64 (Vulkan)
- Ubuntu x64 (ROCm 7.2)
- Ubuntu x64 (OpenVINO)
- Ubuntu x64 (SYCL FP32) DISABLED
Android:
- Android arm64 (CPU)
Windows:
- Windows x64 (CPU)
- Windows arm64 (CPU)
- Windows x64 (CUDA 12) - CUDA 12.4 DLLs
- Windows x64 (CUDA 13) - CUDA 13.3 DLLs
- Windows x64 (Vulkan)
- Windows x64 (SYCL) DISABLED
- Windows x64 (HIP)
openEuler:
- DISABLED
- openEuler x86 (310p)
- openEuler x86 (910b, ACL Graph)
- openEuler aarch64 (310p)
- openEuler aarch64 (910b, ACL Graph)
UI:
- UI

vendor : update cpp-httplib to 0.47.0 (#24395)
Signed-off-by: Adrien Gallouët angt@huggingface.co
macOS/iOS:
- macOS Apple Silicon (arm64)
- macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED
- macOS Intel (x64)
- iOS XCFramework
Linux:
- Ubuntu x64 (CPU)
- Ubuntu arm64 (CPU)
- Ubuntu s390x (CPU)
- Ubuntu x64 (Vulkan)
- Ubuntu arm64 (Vulkan)
- Ubuntu x64 (ROCm 7.2)
- Ubuntu x64 (OpenVINO)
- Ubuntu x64 (SYCL FP32) DISABLED
Android:
- Android arm64 (CPU)
Windows:
- Windows x64 (CPU)
- Windows arm64 (CPU)
- Windows x64 (CUDA 12) - CUDA 12.4 DLLs
- Windows x64 (CUDA 13) - CUDA 13.3 DLLs
- Windows x64 (Vulkan)
- Windows x64 (SYCL) DISABLED
- Windows x64 (HIP)
openEuler:
- DISABLED
- openEuler x86 (310p)
- openEuler x86 (910b, ACL Graph)
- openEuler aarch64 (310p)
- openEuler aarch64 (910b, ACL Graph)
UI:
- UI

graph: Fix granite speech model inference by applying embedding scale when deepstack is not used (#24357)
- llama-graph : apply embedding scale when deepstack is not used
- nits: remove non-existant hunyuan-vl from the tests
- apply suggestion from @gabe-l-hart
Co-authored-by: Xuan Son Nguyen son@huggingface.co
macOS/iOS:
- macOS Apple Silicon (arm64)
- macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED
- macOS Intel (x64)
- iOS XCFramework
Linux:
- Ubuntu x64 (CPU)
- Ubuntu arm64 (CPU)
- Ubuntu s390x (CPU)
- Ubuntu x64 (Vulkan)
- Ubuntu arm64 (Vulkan)
- Ubuntu x64 (ROCm 7.2)
- Ubuntu x64 (OpenVINO)
- Ubuntu x64 (SYCL FP32) DISABLED
Android:
- Android arm64 (CPU)
Windows:
- Windows x64 (CPU)
- Windows arm64 (CPU)
- Windows x64 (CUDA 12) - CUDA 12.4 DLLs
- Windows x64 (CUDA 13) - CUDA 13.3 DLLs
- Windows x64 (Vulkan)
- Windows x64 (SYCL) DISABLED
- Windows x64 (HIP)
openEuler:
- DISABLED
- openEuler x86 (310p)
- openEuler x86 (910b, ACL Graph)
- openEuler aarch64 (310p)
- openEuler aarch64 (910b, ACL Graph)
UI:
- UI

common : relax sampler name matching (#23744)
- common : relax sampler name matching
Currently, in some cases, the alternative names for samplers (like
top-k and min-p instead of the canonical top_k and min_p) are
not always recognized by the common_sampler_types_from_names function
in common/sampling.cpp.
This PR changes the signature of this function to remove the bool allow_alt_names flag, and removes all occurences of the flag from call
sites. Therefore, the function will now always match all known names.
I also changed the logic of the function to unconditionally check the
provided sampler names against both the canonical and alternative names,
and to be case-insensitive.
This fixes an issue I was seeing wherein samplers specified in the
llama-server UI were not recognized as valid when the alternative
names were used.
- add more alt names
- cont. fix
- cast to unsigned char for correctness
- common : unify sampler name mapping
- annotate canonical vs. alt sampler name mappings per @CISC
- Update common/sampling.cpp
Co-authored-by: Sigbjørn Skjæret sigbjorn.skjaeret@scala.com
- common : auto-generate sampler name aliases per @ngxson
- use merged map for matching
- use .merge instead of iterating
- nit: simplify comment
- nit: use insert everywhere, not index assignment
Co-authored-by: Sigbjørn Skjæret sigbjorn.skjaeret@scala.com
macOS/iOS:
- macOS Apple Silicon (arm64)
- macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED
- macOS Intel (x64)
- iOS XCFramework
Linux:
- Ubuntu x64 (CPU)
- Ubuntu arm64 (CPU)
- Ubuntu s390x (CPU)
- Ubuntu x64 (Vulkan)
- Ubuntu arm64 (Vulkan)
- Ubuntu x64 (ROCm 7.2)
- Ubuntu x64 (OpenVINO)
- Ubuntu x64 (SYCL FP32) DISABLED
Android:
- Android arm64 (CPU)
Windows:
- Windows x64 (CPU)
- Windows arm64 (CPU)
- Windows x64 (CUDA 12) - CUDA 12.4 DLLs
- Windows x64 (CUDA 13) - CUDA 13.3 DLLs
- Windows x64 (Vulkan)
- Windows x64 (SYCL) DISABLED
- Windows x64 (HIP)
openEuler:
- DISABLED
- openEuler x86 (310p)
- openEuler x86 (910b, ACL Graph)
- openEuler aarch64 (310p)
- openEuler aarch64 (910b, ACL Graph)
UI:
- UI

common/chat : fix LFM2/LFM2.5 reasoning round-trip and leak (#24234)
- common/chat : fix LFM2 reasoning round-trip and stray leak
- Gate by reasoning format and whether the template supports
macOS/iOS:
- macOS Apple Silicon (arm64)
- macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED
- macOS Intel (x64)
- iOS XCFramework
Linux:
- Ubuntu x64 (CPU)
- Ubuntu arm64 (CPU)
- Ubuntu s390x (CPU)
- Ubuntu x64 (Vulkan)
- Ubuntu arm64 (Vulkan)
- Ubuntu x64 (ROCm 7.2)
- Ubuntu x64 (OpenVINO)
- Ubuntu x64 (SYCL FP32) DISABLED
Android:
- Android arm64 (CPU)
Windows:
- Windows x64 (CPU)
- Windows arm64 (CPU)
- Windows x64 (CUDA 12) - CUDA 12.4 DLLs
- Windows x64 (CUDA 13) - CUDA 13.3 DLLs
- Windows x64 (Vulkan)
- Windows x64 (SYCL) DISABLED
- Windows x64 (HIP)
openEuler:
- DISABLED
- openEuler x86 (310p)
- openEuler x86 (910b, ACL Graph)
- openEuler aarch64 (310p)
- openEuler aarch64 (910b, ACL Graph)
UI:
- UI

model : rename local n_layer_all variable (#24209)
macOS/iOS:
- macOS Apple Silicon (arm64)
- macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED
- macOS Intel (x64)
- iOS XCFramework
Linux:
- Ubuntu x64 (CPU)
- Ubuntu arm64 (CPU)
- Ubuntu s390x (CPU)
- Ubuntu x64 (Vulkan)
- Ubuntu arm64 (Vulkan)
- Ubuntu x64 (ROCm 7.2)
- Ubuntu x64 (OpenVINO)
- Ubuntu x64 (SYCL FP32) DISABLED
Android:
- Android arm64 (CPU)
Windows:
- Windows x64 (CPU)
- Windows arm64 (CPU)
- Windows x64 (CUDA 12) - CUDA 12.4 DLLs
- Windows x64 (CUDA 13) - CUDA 13.3 DLLs
- Windows x64 (Vulkan)
- Windows x64 (SYCL) DISABLED
- Windows x64 (HIP)
openEuler:
- DISABLED
- openEuler x86 (310p)
- openEuler x86 (910b, ACL Graph)
- openEuler aarch64 (310p)
- openEuler aarch64 (910b, ACL Graph)
UI:
- UI

sycl : port multi-column MMVQ from CUDA backend (#21845)
mmvq:
Port the ncols_dst optimization from ggml-cuda/mmvq.cu to SYCL.
Read weights once per dispatch instead of once per column.
Covers all standard quant types + reorder paths for Q4_0, Q8_0,
Q3_K, Q4_K, Q5_K, Q6_K. IQ types (except IQ4_XS) excluded due to
incompatible vec_dot signatures.
ggml-sycl:
The weight reorder was only bootstrapped on single-token mat-vec
(ne[1] == 1). Speculative / MTP verify issues only multi-column mat-vec,
so it never triggered the reorder and ran on the slower non-reorder
kernel. Bootstrap it on small multi-column batches (ne[1] <= 8) too.
macOS/iOS:
- macOS Apple Silicon (arm64)
- macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED
- macOS Intel (x64)
- iOS XCFramework
Linux:
- Ubuntu x64 (CPU)
- Ubuntu arm64 (CPU)
- Ubuntu s390x (CPU)
- Ubuntu x64 (Vulkan)
- Ubuntu arm64 (Vulkan)
- Ubuntu x64 (ROCm 7.2)
- Ubuntu x64 (OpenVINO)
- Ubuntu x64 (SYCL FP32) DISABLED
Android:
- Android arm64 (CPU)
Windows:
- Windows x64 (CPU)
- Windows arm64 (CPU)
- Windows x64 (CUDA 12) - CUDA 12.4 DLLs
- Windows x64 (CUDA 13) - CUDA 13.3 DLLs
- Windows x64 (Vulkan)
- Windows x64 (SYCL) DISABLED
- Windows x64 (HIP)
openEuler:
- DISABLED
- openEuler x86 (310p)
- openEuler x86 (910b, ACL Graph)
- openEuler aarch64 (310p)
- openEuler aarch64 (910b, ACL Graph)
UI:
- UI

metal : reduce rset heartbeat from 500ms -> 5ms (#24074)
macOS/iOS:
- macOS Apple Silicon (arm64)
- macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED
- macOS Intel (x64)
- iOS XCFramework
Linux:
- Ubuntu x64 (CPU)
- Ubuntu arm64 (CPU)
- Ubuntu s390x (CPU)
- Ubuntu x64 (Vulkan)
- Ubuntu arm64 (Vulkan)
- Ubuntu x64 (ROCm 7.2)
- Ubuntu x64 (OpenVINO)
- Ubuntu x64 (SYCL FP32) DISABLED
Android:
- Android arm64 (CPU)
Windows:
- Windows x64 (CPU)
- Windows arm64 (CPU)
- Windows x64 (CUDA 12) - CUDA 12.4 DLLs
- Windows x64 (CUDA 13) - CUDA 13.3 DLLs
- Windows x64 (Vulkan)
- Windows x64 (SYCL) DISABLED
- Windows x64 (HIP)
openEuler:
- DISABLED
- openEuler x86 (310p)
- openEuler x86 (910b, ACL Graph)
- openEuler aarch64 (310p)
- openEuler aarch64 (910b, ACL Graph)
UI:
- UI

hexagon: add gelu_quick (#24007)
macOS/iOS:
- macOS Apple Silicon (arm64)
- macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED
- macOS Intel (x64)
- iOS XCFramework
Linux:
- Ubuntu x64 (CPU)
- Ubuntu arm64 (CPU)
- Ubuntu s390x (CPU)
- Ubuntu x64 (Vulkan)
- Ubuntu arm64 (Vulkan)
- Ubuntu x64 (ROCm 7.2)
- Ubuntu x64 (OpenVINO)
- Ubuntu x64 (SYCL FP32) DISABLED
Android:
- Android arm64 (CPU)
Windows:
- Windows x64 (CPU)
- Windows arm64 (CPU)
- Windows x64 (CUDA 12) - CUDA 12.4 DLLs
- Windows x64 (CUDA 13) - CUDA 13.3 DLLs
- Windows x64 (Vulkan)
- Windows x64 (SYCL) DISABLED
- Windows x64 (HIP)
openEuler:
- DISABLED
- openEuler x86 (310p)
- openEuler x86 (910b, ACL Graph)
- openEuler aarch64 (310p)
- openEuler aarch64 (910b, ACL Graph)
UI:
- UI

server : handle If-None-Match weak ETags (#23916)
macOS/iOS:
- macOS Apple Silicon (arm64)
- macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED
- macOS Intel (x64)
- iOS XCFramework
Linux:
- Ubuntu x64 (CPU)
- Ubuntu arm64 (CPU)
- Ubuntu s390x (CPU)
- Ubuntu x64 (Vulkan)
- Ubuntu arm64 (Vulkan)
- Ubuntu x64 (ROCm 7.2)
- Ubuntu x64 (OpenVINO)
- Ubuntu x64 (SYCL FP32) DISABLED
Android:
- Android arm64 (CPU)
Windows:
- Windows x64 (CPU)
- Windows arm64 (CPU)
- Windows x64 (CUDA 12) - CUDA 12.4 DLLs
- Windows x64 (CUDA 13) - CUDA 13.3 DLLs
- Windows x64 (Vulkan)
- Windows x64 (SYCL) DISABLED
- Windows x64 (HIP)
openEuler:
- DISABLED
- openEuler x86 (310p)
- openEuler x86 (910b, ACL Graph)
- openEuler aarch64 (310p)
- openEuler aarch64 (910b, ACL Graph)
UI:
- UI

Support -fa auto in llama-bench (#23714)
- Support -fa auto in llama-bench
Make the default value of -ngl -1, similar to other tools.
Update README with latest usage and examples
- Address review comments
macOS/iOS:
- macOS Apple Silicon (arm64)
- macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED
- macOS Intel (x64)
- iOS XCFramework
Linux:
- Ubuntu x64 (CPU)
- Ubuntu arm64 (CPU)
- Ubuntu s390x (CPU)
- Ubuntu x64 (Vulkan)
- Ubuntu arm64 (Vulkan)
- Ubuntu x64 (ROCm 7.2)
- Ubuntu x64 (OpenVINO)
- Ubuntu x64 (SYCL FP32) DISABLED
Android:
- Android arm64 (CPU)
Windows:
- Windows x64 (CPU)
- Windows arm64 (CPU)
- Windows x64 (CUDA 12) - CUDA 12.4 DLLs
- Windows x64 (CUDA 13) - CUDA 13.3 DLLs
- Windows x64 (Vulkan)
- Windows x64 (SYCL) DISABLED
- Windows x64 (HIP)
openEuler:
- DISABLED
- openEuler x86 (310p)
- openEuler x86 (910b, ACL Graph)
- openEuler aarch64 (310p)
- openEuler aarch64 (910b, ACL Graph)
UI:
- UI

download: add option to skip_download (#23059)
- download: add option to skip_download
- fix
- fix 2
- if file doesn't exist, respect skip_download flag
macOS/iOS:
- macOS Apple Silicon (arm64)
- macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED
- macOS Intel (x64)
- iOS XCFramework
Linux:
- Ubuntu x64 (CPU)
- Ubuntu arm64 (CPU)
- Ubuntu s390x (CPU)
- Ubuntu x64 (Vulkan)
- Ubuntu arm64 (Vulkan)
- Ubuntu x64 (ROCm 7.2)
- Ubuntu x64 (OpenVINO)
- Ubuntu x64 (SYCL FP32) DISABLED
Android:
- Android arm64 (CPU)
Windows:
- Windows x64 (CPU)
- Windows arm64 (CPU)
- Windows x64 (CUDA 12) - CUDA 12.4 DLLs
- Windows x64 (CUDA 13) - CUDA 13.3 DLLs
- Windows x64 (Vulkan)
- Windows x64 (SYCL) DISABLED
- Windows x64 (HIP)
openEuler:
- DISABLED
- openEuler x86 (310p)
- openEuler x86 (910b, ACL Graph)
- openEuler aarch64 (310p)
- openEuler aarch64 (910b, ACL Graph)
UI:
- UI

mtmd-debug: add color and rainbow mode (#23829)
- mtmd-debug: add color and rainbow mode
- fix M_PI
- max_dist
macOS/iOS:
- macOS Apple Silicon (arm64)
- macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED
- macOS Intel (x64)
- iOS XCFramework
Linux:
- Ubuntu x64 (CPU)
- Ubuntu arm64 (CPU)
- Ubuntu s390x (CPU)
- Ubuntu x64 (Vulkan)
- Ubuntu arm64 (Vulkan)
- Ubuntu x64 (ROCm 7.2)
- Ubuntu x64 (OpenVINO)
- Ubuntu x64 (SYCL FP32) DISABLED
Android:
- Android arm64 (CPU)
Windows:
- Windows x64 (CPU)
- Windows arm64 (CPU)
- Windows x64 (CUDA 12) - CUDA 12.4 DLLs
- Windows x64 (CUDA 13) - CUDA 13.3 DLLs
- Windows x64 (Vulkan)
- Windows x64 (SYCL) DISABLED
- Windows x64 (HIP)
openEuler:
- DISABLED
- openEuler x86 (310p)
- openEuler x86 (910b, ACL Graph)
- openEuler aarch64 (310p)
- openEuler aarch64 (910b, ACL Graph)
UI:
- UI

ggml-webgpu: remove legacy constants (#23672)
macOS/iOS:
- macOS Apple Silicon (arm64)
- macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED
- macOS Intel (x64)
- iOS XCFramework
Linux:
- Ubuntu x64 (CPU)
- Ubuntu arm64 (CPU)
- Ubuntu s390x (CPU)
- Ubuntu x64 (Vulkan)
- Ubuntu arm64 (Vulkan)
- Ubuntu x64 (ROCm 7.2)
- Ubuntu x64 (OpenVINO)
- Ubuntu x64 (SYCL FP32) DISABLED
Android:
- Android arm64 (CPU)
Windows:
- Windows x64 (CPU)
- Windows arm64 (CPU)
- Windows x64 (CUDA 12) - CUDA 12.4 DLLs
- Windows x64 (CUDA 13) - CUDA 13.3 DLLs
- Windows x64 (Vulkan)
- Windows x64 (SYCL) DISABLED
- Windows x64 (HIP)
openEuler:
- DISABLED
- openEuler x86 (310p)
- openEuler x86 (910b, ACL Graph)
- openEuler aarch64 (310p)
- openEuler aarch64 (910b, ACL Graph)
UI:
- UI

convert: add MiniCPM5 tokenizer support (#23384)
Add minicpm5 pre-tokenizer hash via convert_hf_to_gguf_update.py and
implement hardcoded regex handling in llama-vocab.cpp, consistent with
other BPE pre-tokenizers.
Co-authored-by: zhangtao zhangtao2@modelbest.cn
macOS/iOS:
- macOS Apple Silicon (arm64)
- macOS Apple Silicon (arm64, KleidiAI enabled)
- macOS Intel (x64)
- iOS XCFramework
Linux:
- Ubuntu x64 (CPU)
- Ubuntu arm64 (CPU)
- Ubuntu s390x (CPU)
- Ubuntu x64 (Vulkan)
- Ubuntu arm64 (Vulkan)
- Ubuntu x64 (ROCm 7.2)
- Ubuntu x64 (OpenVINO)
- Ubuntu x64 (SYCL FP32) DISABLED
Android:
- Android arm64 (CPU)
Windows:
- Windows x64 (CPU)
- Windows arm64 (CPU)
- Windows x64 (CUDA 12) - CUDA 12.4 DLLs
- Windows x64 (CUDA 13) - CUDA 13.1 DLLs
- Windows x64 (Vulkan)
- Windows x64 (SYCL) DISABLED
- Windows x64 (HIP)
openEuler:
- DISABLED
- openEuler x86 (310p)
- openEuler x86 (910b, ACL Graph)
- openEuler aarch64 (310p)
- openEuler aarch64 (910b, ACL Graph)
UI:
- UI

server: fix checkpoints creation (#22929)
- common : add common_chat_split_by_role
- cont : fix spans to reach end of message
- server: fix checkpoints creation
- extract message_spans from chat templates
- find the prompt token position before the latest user message
- split prompt batching at that position
- create a context checkpoint before the latest user input
- avoid periodic mid-prompt checkpoints when that position is known
- handle multimodal prompts when mapping text/template positions to server prompt tokens
- add --checkpoint-min-step to control minimum spacing between checkpoints
- cont : clean-up
- Support autoparser detection for message barriers
- server: fix message span delimiter and update docs
Co-authored-by: Alde Rojas hello@alde.dev
Co-authored-by: Georgi Gerganov ggerganov@gmail.com
Co-authored-by: Piotr Wilkin piotr.wilkin@syndatis.com
macOS/iOS:
- macOS Apple Silicon (arm64)
- macOS Apple Silicon (arm64, KleidiAI enabled)
- macOS Intel (x64)
- iOS XCFramework
Linux:
- Ubuntu x64 (CPU)
- Ubuntu arm64 (CPU)
- Ubuntu s390x (CPU)
- Ubuntu x64 (Vulkan)
- Ubuntu arm64 (Vulkan)
- Ubuntu x64 (ROCm 7.2)
- Ubuntu x64 (OpenVINO)
- Ubuntu x64 (SYCL FP32)
- Ubuntu x64 (SYCL FP16)
Android:
- Android arm64 (CPU)
Windows:
- Windows x64 (CPU)
- Windows arm64 (CPU)
- Windows x64 (CUDA 12) - CUDA 12.4 DLLs
- Windows x64 (CUDA 13) - CUDA 13.1 DLLs
- Windows x64 (Vulkan)
- Windows x64 (SYCL)
- Windows x64 (HIP)
openEuler:
- openEuler x86 (310p)
- openEuler x86 (910b, ACL Graph)
- openEuler aarch64 (310p)
- openEuler aarch64 (910b, ACL Graph)
UI:
- UI

model : add NVFP4 MTP scale tensors (#23563)
- Add NVFP4 MTP scale tensors
- Link Qwen3.5 MTP tensors
- Aligned nullptr
macOS/iOS:
- macOS Apple Silicon (arm64)
- macOS Apple Silicon (arm64, KleidiAI enabled)
- macOS Intel (x64)
- iOS XCFramework
Linux:
- Ubuntu x64 (CPU)
- Ubuntu arm64 (CPU)
- Ubuntu s390x (CPU)
- Ubuntu x64 (Vulkan)
- Ubuntu arm64 (Vulkan)
- Ubuntu x64 (ROCm 7.2)
- Ubuntu x64 (OpenVINO)
- Ubuntu x64 (SYCL FP32)
- Ubuntu x64 (SYCL FP16)
Android:
- Android arm64 (CPU)
Windows:
- Windows x64 (CPU)
- Windows arm64 (CPU)
- Windows x64 (CUDA 12) - CUDA 12.4 DLLs
- Windows x64 (CUDA 13) - CUDA 13.1 DLLs
- Windows x64 (Vulkan)
- Windows x64 (SYCL)
- Windows x64 (HIP)
openEuler:
- openEuler x86 (310p)
- openEuler x86 (910b, ACL Graph)
- openEuler aarch64 (310p)
- openEuler aarch64 (910b, ACL Graph)

opencl: generalize Adreno MoE kernels on M (#23449)
macOS/iOS:
- macOS Apple Silicon (arm64)
- macOS Apple Silicon (arm64, KleidiAI enabled)
- macOS Intel (x64)
- iOS XCFramework
Linux:
- Ubuntu x64 (CPU)
- Ubuntu arm64 (CPU)
- Ubuntu s390x (CPU)
- Ubuntu x64 (Vulkan)
- Ubuntu arm64 (Vulkan)
- Ubuntu x64 (ROCm 7.2)
- Ubuntu x64 (OpenVINO)
- Ubuntu x64 (SYCL FP32)
- Ubuntu x64 (SYCL FP16)
Android:
- Android arm64 (CPU)
Windows:
- Windows x64 (CPU)
- Windows arm64 (CPU)
- Windows x64 (CUDA 12) - CUDA 12.4 DLLs
- Windows x64 (CUDA 13) - CUDA 13.1 DLLs
- Windows x64 (Vulkan)
- Windows x64 (SYCL)
- Windows x64 (HIP)
openEuler:
- openEuler x86 (310p)
- openEuler x86 (910b, ACL Graph)
- openEuler aarch64 (310p)
- openEuler aarch64 (910b, ACL Graph)

vulkan: fuse snake activation (mul, sin, sqr, mul, add) (#22855)
- vulkan: fuse snake activation (mul, sin, sqr, mul, add)
Add snake.comp shader with F32 / F16 / BF16 pipelines and
ggml_vk_snake_dispatch_fused. The matcher recognizes the naive 5 op
decomposition emitted by audio decoders (BigVGAN, Vocos) for snake
activation y = x + sin(a*x)^2 * inv_b and rewrites it to a single
elementwise kernel.
test_snake_fuse from the CUDA PR now also compares CPU naive vs
Vulkan fused across F32 / F16 / BF16.
- vulkan: address jeffbolznv review for fused snake activation
Rename T / C to ne0 / ne1 in the shader and push constants to match
the standard naming convention used across the Vulkan backend.
Tighten ggml_vk_can_fuse_snake: require x and dst to be contiguous
(the shader uses idx = i0 + i1 * ne0) and require a / inv_b to be
tightly packed on the broadcast dim (the shader reads data_a[i1]).
- vulkan: tighten snake fusion type checks for all operands (address jeffbolznv review)
- vulkan: reject snake fusion when ne[2] or ne[3] > 1 (address jeffbolznv review)
- vulkan: address 0cc4m review for fused snake activation
snake.comp is renamed to follow the ggml DATA_A_* / A_TYPE convention.
A_TYPE now applies to the activation tensor data_a instead of the
broadcast multiplier, and the bindings become data_a (A_TYPE), data_b
(float), data_c (float) and data_d (D_TYPE). A header at the top of
the shader maps each buffer to its role in y = x + sin(b * x)^2 * c.
On the C++ side, ggml_vk_can_fuse_snake reuses the existing snake_pattern
constant instead of duplicating the op list, sin_node is extracted as a
named local alongside the other chain nodes, and the broadcast operands
a and inv_b are now required to be GGML_TYPE_F32 to match the hardcoded
float bindings on data_b and data_c (the previous a->type == x->type
would silently reject any future BF16 or F16 chain once the supports_op
gate for SIN / SQR is lifted). ggml_vk_snake_dispatch_fused gets an
explicit GGML_TYPE_F32 case and GGML_ABORT on default in place of the
silent f32 fallback, and a stale comment about data_a[i1] / data_inv_b[i1]
is refreshed to match the new binding names.
macOS/iOS:
- macOS Apple Silicon (arm64)
- macOS Apple Silicon (arm64, KleidiAI enabled)
- macOS Intel (x64)
- iOS XCFramework
Linux:
- Ubuntu x64 (CPU)
- Ubuntu arm64 (CPU)
- Ubuntu s390x (CPU)
- Ubuntu x64 (Vulkan)
- Ubuntu arm64 (Vulkan)
- Ubuntu x64 (ROCm 7.2)
- Ubuntu x64 (OpenVINO)
- Ubuntu x64 (SYCL FP32)
- Ubuntu x64 (SYCL FP16)
Android:
- Android arm64 (CPU)
Windows:
- Windows x64 (CPU)
- Windows arm64 (CPU)
- Windows x64 (CUDA 12) - CUDA 12.4 DLLs
- Windows x64 (CUDA 13) - CUDA 13.1 DLLs
- Windows x64 (Vulkan)
- Windows x64 (SYCL)
- Windows x64 (HIP)
openEuler:
- openEuler x86 (310p)
- openEuler x86 (910b, ACL Graph)
- openEuler aarch64 (310p)
- openEuler aarch64 (910b, ACL Graph)

app : show version (#23426)
Signed-off-by: Adrien Gallouët angt@huggingface.co
macOS/iOS:
- macOS Apple Silicon (arm64)
- macOS Apple Silicon (arm64, KleidiAI enabled)
- macOS Intel (x64)
- iOS XCFramework
Linux:
- Ubuntu x64 (CPU)
- Ubuntu arm64 (CPU)
- Ubuntu s390x (CPU)
- Ubuntu x64 (Vulkan)
- Ubuntu arm64 (Vulkan)
- Ubuntu x64 (ROCm 7.2)
- Ubuntu x64 (OpenVINO)
- Ubuntu x64 (SYCL FP32)
- Ubuntu x64 (SYCL FP16)
Android:
- Android arm64 (CPU)
Windows:
- Windows x64 (CPU)
- Windows arm64 (CPU)
- Windows x64 (CUDA 12) - CUDA 12.4 DLLs
- Windows x64 (CUDA 13) - CUDA 13.1 DLLs
- Windows x64 (Vulkan)
- Windows x64 (SYCL)
- Windows x64 (HIP)
openEuler:
- openEuler x86 (310p)
- openEuler x86 (910b, ACL Graph)
- openEuler aarch64 (310p)
- openEuler aarch64 (910b, ACL Graph)

ggml-cuda: tune RDNA3 Q6_K MMVQ nwarps (#23349)
macOS/iOS:
- macOS Apple Silicon (arm64)
- macOS Apple Silicon (arm64, KleidiAI enabled)
- macOS Intel (x64)
- iOS XCFramework
Linux:
- Ubuntu x64 (CPU)
- Ubuntu arm64 (CPU)
- Ubuntu s390x (CPU)
- Ubuntu x64 (Vulkan)
- Ubuntu arm64 (Vulkan)
- Ubuntu x64 (ROCm 7.2)
- Ubuntu x64 (OpenVINO)
- Ubuntu x64 (SYCL FP32)
- Ubuntu x64 (SYCL FP16)
Android:
- Android arm64 (CPU)
Windows:
- Windows x64 (CPU)
- Windows arm64 (CPU)
- Windows x64 (CUDA 12) - CUDA 12.4 DLLs
- Windows x64 (CUDA 13) - CUDA 13.1 DLLs
- Windows x64 (Vulkan)
- Windows x64 (SYCL)
- Windows x64 (HIP)
openEuler:
- openEuler x86 (310p)
- openEuler x86 (910b, ACL Graph)
- openEuler aarch64 (310p)
- openEuler aarch64 (910b, ACL Graph)

hexagon: add support for TRI op (#22822)
- Hexagon: TRI HVX Kernel addition to ggml hexagon HTP ops and context
- addressed PR review comments for TRI op
- hexagon: clang format
- hex-unary: remove merge conflict markers
- hex-ggml: remove duplicate op cases (merge conflict)
- hex-ggml: fix editor config errors
Co-authored-by: Todor Boinovski todorb@qti.qualcomm.com
Co-authored-by: Max Krasnyansky maxk@qti.qualcomm.com
macOS/iOS:
- macOS Apple Silicon (arm64)
- macOS Apple Silicon (arm64, KleidiAI enabled)
- macOS Intel (x64)
- iOS XCFramework
Linux:
- Ubuntu x64 (CPU)
- Ubuntu arm64 (CPU)
- Ubuntu s390x (CPU)
- Ubuntu x64 (Vulkan)
- Ubuntu arm64 (Vulkan)
- Ubuntu x64 (ROCm 7.2)
- Ubuntu x64 (OpenVINO)
- Ubuntu x64 (SYCL FP32)
- Ubuntu x64 (SYCL FP16)
Android:
- Android arm64 (CPU)
Windows:
- Windows x64 (CPU)
- Windows arm64 (CPU)
- Windows x64 (CUDA 12) - CUDA 12.4 DLLs
- Windows x64 (CUDA 13) - CUDA 13.1 DLLs
- Windows x64 (Vulkan)
- Windows x64 (SYCL)
- Windows x64 (HIP)
openEuler:
- openEuler x86 (310p)
- openEuler x86 (910b, ACL Graph)
- openEuler aarch64 (310p)
- openEuler aarch64 (910b, ACL Graph)

feat: Support d_conv=15 for ssm-conv.cu (#23017)
Branch: ModalityConditionalAdapters
AI-usage: none
Signed-off-by: Gabe Goodhart ghart@us.ibm.com
macOS/iOS:
- macOS Apple Silicon (arm64)
- macOS Apple Silicon (arm64, KleidiAI enabled)
- macOS Intel (x64)
- iOS XCFramework
Linux:
- Ubuntu x64 (CPU)
- Ubuntu arm64 (CPU)
- Ubuntu s390x (CPU)
- Ubuntu x64 (Vulkan)
- Ubuntu arm64 (Vulkan)
- Ubuntu x64 (ROCm 7.2)
- Ubuntu x64 (OpenVINO)
- Ubuntu x64 (SYCL FP32)
- Ubuntu x64 (SYCL FP16)
Android:
- Android arm64 (CPU)
Windows:
- Windows x64 (CPU)
- Windows arm64 (CPU)
- Windows x64 (CUDA 12) - CUDA 12.4 DLLs
- Windows x64 (CUDA 13) - CUDA 13.1 DLLs
- Windows x64 (Vulkan)
- Windows x64 (SYCL)
- Windows x64 (HIP)
openEuler:
- openEuler x86 (310p)
- openEuler x86 (910b, ACL Graph)
- openEuler aarch64 (310p)
- openEuler aarch64 (910b, ACL Graph)

server: (router) alloc tmp buffer on heap (#23159)
macOS/iOS:
- macOS Apple Silicon (arm64)
- macOS Apple Silicon (arm64, KleidiAI enabled)
- macOS Intel (x64)
- iOS XCFramework
Linux:
- Ubuntu x64 (CPU)
- Ubuntu arm64 (CPU)
- Ubuntu s390x (CPU)
- Ubuntu x64 (Vulkan)
- Ubuntu arm64 (Vulkan)
- Ubuntu x64 (ROCm 7.2)
- Ubuntu x64 (OpenVINO)
- Ubuntu x64 (SYCL FP32)
- Ubuntu x64 (SYCL FP16)
Android:
- Android arm64 (CPU)
Windows:
- Windows x64 (CPU)
- Windows arm64 (CPU)
- Windows x64 (CUDA 12) - CUDA 12.4 DLLs
- Windows x64 (CUDA 13) - CUDA 13.1 DLLs
- Windows x64 (Vulkan)
- Windows x64 (SYCL)
- Windows x64 (HIP)
openEuler:
- openEuler x86 (310p)
- openEuler x86 (910b, ACL Graph)
- openEuler aarch64 (310p)
- openEuler aarch64 (910b, ACL Graph)

ui: Restructure repo to use tools/ui folder and ui / UI / llama-ui / LLAMA_UI naming (#23064)
- webui: Move static build output from tools/server/public to build/ui directory
- refactor: Move to tools/ui
- refactor: rename CMake variables and preprocessor defines
- Rename LLAMA_BUILD_WEBUI -> LLAMA_BUILD_UI (old kept as deprecated)
- Rename LLAMA_USE_PREBUILT_WEBUI -> LLAMA_USE_PREBUILT_UI (old kept as deprecated)
- Backward compat: old vars auto-forward to new ones with DEPRECATION warning
- Rename internal vars: WEBUI_SOURCE -> UI_SOURCE, WEBUI_SOURCE_DIR -> UI_SOURCE_DIR, etc.
- Rename HF bucket: LLAMA_WEBUI_HF_BUCKET -> LLAMA_UI_HF_BUCKET
- Emit both LLAMA_BUILD_WEBUI and LLAMA_BUILD_UI preprocessor defines
- Emit both LLAMA_WEBUI_DEFAULT_ENABLED and LLAMA_UI_DEFAULT_ENABLED
- refactor: rename CLI flags (--webui -> --ui) with backward compat
- Add --ui/--no-ui (old --webui/--no-webui kept as deprecated aliases)
- Add --ui-config (old --webui-config kept as deprecated alias)
- Add --ui-config-file (old --webui-config-file kept as deprecated alias)
- Add --ui-mcp-proxy/--no-ui-mcp-proxy (old --webui-mcp-proxy kept as deprecated)
- Add new env vars: LLAMA_ARG_UI, LLAMA_ARG_UI_CONFIG, LLAMA_ARG_UI_CONFIG_FILE, LLAMA_ARG_UI_MCP_PROXY
- C++ struct fields: params.ui, params.ui_config_json, params.ui_mcp_proxy added alongside old fields
- Backward compat: old fields synced to new ones in g_params_to_internals
- refactor: update C++ server internals with backward compat
- Rename json_webui_settings -> json_ui_settings (both kept in server_context_meta)
- Rename params.webui usage -> params.ui (both synced, old still works)
- JSON API emits both "ui"/"ui_settings" and "webui"/"webui_settings" keys
- Server routes use params.ui_mcp_proxy || params.webui_mcp_proxy
- Preprocessor guards use #if defined(LLAMA_BUILD_UI) || defined(LLAMA_BUILD_WEBUI)
- refactor: rename CI/CD workflows, artifacts, and build script
- Rename webui-build.yml -> ui-build.yml; artifact webui-build -> ui-build
- Rename webui-publish.yml -> ui-publish.yml; var HF_BUCKET_WEBUI_STATIC_OUTPUT -> HF_BUCKET_UI_STATIC_OUTPUT
- Rename server-webui.yml -> server-ui.yml; job webui-build/checks -> ui-build/checks
- Update server.yml: job/artifact refs webui-build -> ui-build
- Update release.yml: all webui-build/publish refs -> ui-build/publish; HF_TOKEN_WEBUI_STATIC_OUTPUT -> HF_TOKEN_UI_STATIC_OUTPUT
- Update server-self-hosted.yml: webui-build -> ui-build
- Update build-self-hosted.yml: HF_WEBUI_VERSION -> HF_UI_VERSION
- Rename webui-download.cmake -> ui-download.cmake (internal refs updated)
- Update labeler.yml: server/webui -> server/ui path label
- docs: update CODEOWNERS and server README docs
- Update CODEOWNERS: team ggml-org/llama-webui -> ggml-org/llama-ui, path /tools/server/webui/ -> /tools/ui/
- Update server README.md: CLI tables show --ui flags with deprecated --webui aliases
- Update server README-dev.md: "WebUI" -> "UI", paths updated to tools/ui/
- fix: Small fixes for UI build
- fix: CMake.txt syntax
- chore: Formatting
- fix: .editorconfig for llama-ui
- chore: Formatting
- refactor: Use APP_NAME in Error route
- refactor: Cleanup
- refactor: Single migration service
- make llama-ui a linkable target
- fix: UI Build output
- fix: Missing change
- fix: separate llama-ui npm build output into build/tools/ui/dist subfolder + use cmake npm build instead of downloading ui-build.yml artifacts in CI
- refactor: UI workflows cleanup
Co-authored-by: Xuan Son Nguyen son@huggingface.co
macOS/iOS:
- macOS Apple Silicon (arm64)
- macOS Apple Silicon (arm64, KleidiAI enabled)
- macOS Intel (x64)
- iOS XCFramework
Linux:
- Ubuntu x64 (CPU)
- Ubuntu arm64 (CPU)
- Ubuntu s390x (CPU)
- Ubuntu x64 (Vulkan)
- Ubuntu arm64 (Vulkan)
- Ubuntu x64 (ROCm 7.2)
- Ubuntu x64 (OpenVINO)
- Ubuntu x64 (SYCL FP32)
- Ubuntu x64 (SYCL FP16)
Android:
- Android arm64 (CPU)
Windows:
- Windows x64 (CPU)
- Windows arm64 (CPU)
- Windows x64 (CUDA 12) - CUDA 12.4 DLLs
- Windows x64 (CUDA 13

ggml-hexagon: cpy: add contiguous fast-path in reshape copy (#23076)
macOS/iOS:
- macOS Apple Silicon (arm64)
- macOS Apple Silicon (arm64, KleidiAI enabled)
- macOS Intel (x64)
- iOS XCFramework
Linux:
- Ubuntu x64 (CPU)
- Ubuntu arm64 (CPU)
- Ubuntu s390x (CPU)
- Ubuntu x64 (Vulkan)
- Ubuntu arm64 (Vulkan)
- Ubuntu x64 (ROCm 7.2)
- Ubuntu x64 (OpenVINO)
- Ubuntu x64 (SYCL FP32)
- Ubuntu x64 (SYCL FP16)
Android:
- Android arm64 (CPU)
Windows:
- Windows x64 (CPU)
- Windows arm64 (CPU)
- Windows x64 (CUDA 12) - CUDA 12.4 DLLs
- Windows x64 (CUDA 13) - CUDA 13.1 DLLs
- Windows x64 (Vulkan)
- Windows x64 (SYCL)
- Windows x64 (HIP)
openEuler:
- openEuler x86 (310p)
- openEuler x86 (910b, ACL Graph)
- openEuler aarch64 (310p)
- openEuler aarch64 (910b, ACL Graph)

ggml-webgpu: only use subgroup-matrix path when head dims are divisible by sg_mat_k / sg_mat_n (#23020)
macOS/iOS:
- macOS Apple Silicon (arm64)
- macOS Apple Silicon (arm64, KleidiAI enabled)
- macOS Intel (x64)
- iOS XCFramework
Linux:
- Ubuntu x64 (CPU)
- Ubuntu arm64 (CPU)
- Ubuntu s390x (CPU)
- Ubuntu x64 (Vulkan)
- Ubuntu arm64 (Vulkan)
- Ubuntu x64 (ROCm 7.2)
- Ubuntu x64 (OpenVINO)
- Ubuntu x64 (SYCL FP32)
- Ubuntu x64 (SYCL FP16)
Android:
- Android arm64 (CPU)
Windows:
- Windows x64 (CPU)
- Windows arm64 (CPU)
- Windows x64 (CUDA 12) - CUDA 12.4 DLLs
- Windows x64 (CUDA 13) - CUDA 13.1 DLLs
- Windows x64 (Vulkan)
- Windows x64 (SYCL)
- Windows x64 (HIP)
openEuler:
- openEuler x86 (310p)
- openEuler x86 (910b, ACL Graph)
- openEuler aarch64 (310p)
- openEuler aarch64 (910b, ACL Graph)

hexagon: eliminate scalar VTCM loads via HVX splat helpers (#22993)
- hexagon: add hvx_vec_repl helpers and use those for splat-from-vtcm usecase
- hmx-mm: optimize per-group scale handling
- hmx-fa: optimize slope load from vtcm
- hmx-fa: use aligned access where possible in hmx-utils
- hexagon: add hvx_vec_repl_2x_f16 helper and consolidate repl helpers
Co-authored-by: Max Krasnyansky maxk@qti.qualcomm.com
macOS/iOS:
- macOS Apple Silicon (arm64)
- macOS Apple Silicon (arm64, KleidiAI enabled)
- macOS Intel (x64)
- iOS XCFramework
Linux:
- Ubuntu x64 (CPU)
- Ubuntu arm64 (CPU)
- Ubuntu s390x (CPU)
- Ubuntu x64 (Vulkan)
- Ubuntu arm64 (Vulkan)
- Ubuntu x64 (ROCm 7.2)
- Ubuntu x64 (OpenVINO)
- Ubuntu x64 (SYCL FP32)
- Ubuntu x64 (SYCL FP16)
Android:
- Android arm64 (CPU)
Windows:
- Windows x64 (CPU)
- Windows arm64 (CPU)
- Windows x64 (CUDA 12) - CUDA 12.4 DLLs
- Windows x64 (CUDA 13) - CUDA 13.1 DLLs
- Windows x64 (Vulkan)
- Windows x64 (SYCL)
- Windows x64 (HIP)
openEuler:
- openEuler x86 (310p)
- openEuler x86 (910b, ACL Graph)
- openEuler aarch64 (310p)
- openEuler aarch64 (910b, ACL Graph)

opencl: add q4_1 MoE for Adreno (#22856)
- Q4_1 MoE CLC pass sanity check
- remove unnecessary code
- opencl: remove unnecessary asserts and reformat
- opencl: fix supports_op for q4_1 moe
- q4_1 moe is supported by Adreno with certain shapes
Co-authored-by: Li He lih@qti.qualcomm.com
macOS/iOS:
- macOS Apple Silicon (arm64)
- macOS Apple Silicon (arm64, KleidiAI enabled)
- macOS Intel (x64)
- iOS XCFramework
Linux:
- Ubuntu x64 (CPU)
- Ubuntu arm64 (CPU)
- Ubuntu s390x (CPU)
- Ubuntu x64 (Vulkan)
- Ubuntu arm64 (Vulkan)
- Ubuntu x64 (ROCm 7.2)
- Ubuntu x64 (OpenVINO)
- Ubuntu x64 (SYCL FP32)
- Ubuntu x64 (SYCL FP16)
Android:
- Android arm64 (CPU)
Windows:
- Windows x64 (CPU)
- Windows arm64 (CPU)
- Windows x64 (CUDA 12) - CUDA 12.4 DLLs
- Windows x64 (CUDA 13) - CUDA 13.1 DLLs
- Windows x64 (Vulkan)
- Windows x64 (SYCL)
- Windows x64 (HIP)
openEuler:
- openEuler x86 (310p)
- openEuler x86 (910b, ACL Graph)
- openEuler aarch64 (310p)
- openEuler aarch64 (910b, ACL Graph)

[SYCL] Add OP im2col_3d (#22903)
- add im2col_3d
- format code
- update the ops.md
macOS/iOS:
- macOS Apple Silicon (arm64)
- macOS Apple Silicon (arm64, KleidiAI enabled)
- macOS Intel (x64)
- iOS XCFramework
Linux:
- Ubuntu x64 (CPU)
- Ubuntu arm64 (CPU)
- Ubuntu s390x (CPU)
- Ubuntu x64 (Vulkan)
- Ubuntu arm64 (Vulkan)
- Ubuntu x64 (ROCm 7.2)
- Ubuntu x64 (OpenVINO)
- Ubuntu x64 (SYCL FP32)
- Ubuntu x64 (SYCL FP16)
Android:
- Android arm64 (CPU)
Windows:
- Windows x64 (CPU)
- Windows arm64 (CPU)
- Windows x64 (CUDA 12) - CUDA 12.4 DLLs
- Windows x64 (CUDA 13) - CUDA 13.1 DLLs
- Windows x64 (Vulkan)
- Windows x64 (SYCL)
- Windows x64 (HIP)
openEuler:
- openEuler x86 (310p)
- openEuler x86 (910b, ACL Graph)
- openEuler aarch64 (310p)
- openEuler aarch64 (910b, ACL Graph)

model : add sarvam_moe architecture support (#20275)
macOS/iOS:
- macOS Apple Silicon (arm64)
- macOS Apple Silicon (arm64, KleidiAI enabled)
- macOS Intel (x64)
- iOS XCFramework
Linux:
- Ubuntu x64 (CPU)
- Ubuntu arm64 (CPU)
- Ubuntu s390x (CPU)
- Ubuntu x64 (Vulkan)
- Ubuntu arm64 (Vulkan)
- Ubuntu x64 (ROCm 7.2)
- Ubuntu x64 (OpenVINO)
- Ubuntu x64 (SYCL FP32)
- Ubuntu x64 (SYCL FP16)
Android:
- Android arm64 (CPU)
Windows:
- Windows x64 (CPU)
- Windows arm64 (CPU)
- Windows x64 (CUDA 12) - CUDA 12.4 DLLs
- Windows x64 (CUDA 13) - CUDA 13.1 DLLs
- Windows x64 (Vulkan)
- Windows x64 (SYCL)
- Windows x64 (HIP)
openEuler:
- openEuler x86 (310p)
- openEuler x86 (910b, ACL Graph)
- openEuler aarch64 (310p)
- openEuler aarch64 (910b, ACL Graph)

Add flash attention MMA / Tiles to support MiMo-V2.5 (#22812)
- mimo-v2.5: add flash attention mma/tiles for for d_kq=192 d_v=128
- mimo-v2.5: follow (256, 256) fattn templates
- mimo-v2.5: cleanup comments
- mimo-v2.5: further comment cleanup
- mimo-v2.5: address PR feedback
fix GQA handling
check for other dangling 320/576 carveouts and mirror them for 192
Add to backend ops test so new paths are covered
macOS/iOS:
- macOS Apple Silicon (arm64)
- macOS Apple Silicon (arm64, KleidiAI enabled)
- macOS Intel (x64)
- iOS XCFramework
Linux:
- Ubuntu x64 (CPU)
- Ubuntu arm64 (CPU)
- Ubuntu s390x (CPU)
- Ubuntu x64 (Vulkan)
- Ubuntu arm64 (Vulkan)
- Ubuntu x64 (ROCm 7.2)
- Ubuntu x64 (OpenVINO)
- Ubuntu x64 (SYCL FP32)
- Ubuntu x64 (SYCL FP16)
Android:
- Android arm64 (CPU)
Windows:
- Windows x64 (CPU)
- Windows arm64 (CPU)
- Windows x64 (CUDA 12) - CUDA 12.4 DLLs
- Windows x64 (CUDA 13) - CUDA 13.1 DLLs
- Windows x64 (Vulkan)
- Windows x64 (SYCL)
- Windows x64 (HIP)
openEuler:
- openEuler x86 (310p)
- openEuler x86 (910b, ACL Graph)
- openEuler aarch64 (310p)
- openEuler aarch64 (910b, ACL Graph)

opencl: add q4_0 MoE GEMM for Adreno (#22731)
- Q4_0 MoE CLC pass sanity check
- release program
- opencl: fix whitespace
- opencl: remove unused cl_program
- opencl: break #if block to make it more clear
- opencl: adjust format
Co-authored-by: Li He lih@qti.qualcomm.com
macOS/iOS:
- macOS Apple Silicon (arm64)
- macOS Apple Silicon (arm64, KleidiAI enabled)
- macOS Intel (x64)
- iOS XCFramework
Linux:
- Ubuntu x64 (CPU)
- Ubuntu arm64 (CPU)
- Ubuntu s390x (CPU)
- Ubuntu x64 (Vulkan)
- Ubuntu arm64 (Vulkan)
- Ubuntu x64 (ROCm 7.2)
- Ubuntu x64 (OpenVINO)
- Ubuntu x64 (SYCL FP32)
- Ubuntu x64 (SYCL FP16)
Android:
- Android arm64 (CPU)
Windows:
- Windows x64 (CPU)
- Windows arm64 (CPU)
- Windows x64 (CUDA 12) - CUDA 12.4 DLLs
- Windows x64 (CUDA 13) - CUDA 13.1 DLLs
- Windows x64 (Vulkan)
- Windows x64 (SYCL)
- Windows x64 (HIP)
openEuler:
- openEuler x86 (310p)
- openEuler x86 (910b, ACL Graph)
- openEuler aarch64 (310p)
- openEuler aarch64 (910b, ACL Graph)

mtmd : support MiniCPM-V 4.6 (#22529)
- Support MiniCPM-V 4.6 in new branch
Signed-off-by: tc-mb tianchi_cai@icloud.com
- fix code bug
Signed-off-by: tc-mb tianchi_cai@icloud.com
- fix pre-commit
Signed-off-by: tc-mb tianchi_cai@icloud.com
- fix convert
Signed-off-by: tc-mb tianchi_cai@icloud.com
- rename clip_graph_minicpmv4_6
Signed-off-by: tc-mb tianchi_cai@icloud.com
- use new TYPE_MINICPMV4_6
Signed-off-by: tc-mb tianchi_cai@icloud.com
- use build_attn to allow flash attention support
Signed-off-by: tc-mb tianchi_cai@icloud.com
- no use legacy code, restored here.
Signed-off-by: tc-mb tianchi_cai@icloud.com
- use the existing tensors name
Signed-off-by: tc-mb tianchi_cai@icloud.com
- unused ctx->model.hparams.minicpmv_version
Signed-off-by: tc-mb tianchi_cai@icloud.com
- use n_merge for slice alignment
Signed-off-by: tc-mb tianchi_cai@icloud.com
- borrow wa_layer_indexes for vit_merger insertion point
Signed-off-by: tc-mb tianchi_cai@icloud.com
- fix code style
Signed-off-by: tc-mb tianchi_cai@icloud.com
- Update convert_hf_to_gguf.py
Co-authored-by: Sigbjørn Skjæret sigbjorn.skjaeret@scala.com
- use filter_tensors and add model.vision_tower
Signed-off-by: tc-mb tianchi_cai@icloud.com
- fix chkhsh
Signed-off-by: tc-mb tianchi_cai@icloud.com
- fix type check
Signed-off-by: tc-mb tianchi_cai@icloud.com
Signed-off-by: tc-mb tianchi_cai@icloud.com
Co-authored-by: Sigbjørn Skjæret sigbjorn.skjaeret@scala.com
macOS/iOS:
- macOS Apple Silicon (arm64)
- macOS Apple Silicon (arm64, KleidiAI enabled)
- macOS Intel (x64)
- iOS XCFramework
Linux:
- Ubuntu x64 (CPU)
- Ubuntu arm64 (CPU)
- Ubuntu s390x (CPU)
- Ubuntu x64 (Vulkan)
- Ubuntu arm64 (Vulkan)
- Ubuntu x64 (ROCm 7.2)
- Ubuntu x64 (OpenVINO)
- Ubuntu x64 (SYCL FP32)
- Ubuntu x64 (SYCL FP16)
Android:
- Android arm64 (CPU)
Windows:
- Windows x64 (CPU)
- Windows arm64 (CPU)
- Windows x64 (CUDA 12) - CUDA 12.4 DLLs
- Windows x64 (CUDA 13) - CUDA 13.1 DLLs
- Windows x64 (Vulkan)
- Windows x64 (SYCL)
- Windows x64 (HIP)
openEuler:
- openEuler x86 (310p)
- openEuler x86 (910b, ACL Graph)
- openEuler aarch64 (310p)
- openEuler aarch64 (910b, ACL Graph)

ggml : use CL_DEVICE_GLOBAL_MEM_SIZE as memory estimate for OpenCL --fit (#22688)
- ggml : report estimated OpenCL memory for --fit
Signed-off-by: Florian Reinle f.reinle@otec.de
- ggml : estimated OpenCL memory backend integrated
Signed-off-by: Florian Reinle f.reinle@otec.de
Signed-off-by: Florian Reinle f.reinle@otec.de
macOS/iOS:
- macOS Apple Silicon (arm64)
- macOS Apple Silicon (arm64, KleidiAI enabled)
- macOS Intel (x64)
- iOS XCFramework
Linux:
- Ubuntu x64 (CPU)
- Ubuntu arm64 (CPU)
- Ubuntu s390x (CPU)
- Ubuntu x64 (Vulkan)
- Ubuntu arm64 (Vulkan)
- Ubuntu x64 (ROCm 7.2)
- Ubuntu x64 (OpenVINO)
- Ubuntu x64 (SYCL FP32)
- Ubuntu x64 (SYCL FP16)
Android:
- Android arm64 (CPU)
Windows:
- Windows x64 (CPU)
- Windows arm64 (CPU)
- Windows x64 (CUDA 12) - CUDA 12.4 DLLs
- Windows x64 (CUDA 13) - CUDA 13.1 DLLs
- Windows x64 (Vulkan)
- Windows x64 (SYCL)
- Windows x64 (HIP)
openEuler:
- openEuler x86 (310p)
- openEuler x86 (910b, ACL Graph)
- openEuler aarch64 (310p)
- openEuler aarch64 (910b, ACL Graph)

ggml : implement fast walsh-hadamard transform for kv rotation (#21352) (#22631)
macOS/iOS:
- macOS Apple Silicon (arm64)
- macOS Apple Silicon (arm64, KleidiAI enabled)
- macOS Intel (x64)
- iOS XCFramework
Linux:
- Ubuntu x64 (CPU)
- Ubuntu arm64 (CPU)
- Ubuntu s390x (CPU)
- Ubuntu x64 (Vulkan)
- Ubuntu arm64 (Vulkan)
- Ubuntu x64 (ROCm 7.2)
- Ubuntu x64 (OpenVINO)
- Ubuntu x64 (SYCL FP32)
- Ubuntu x64 (SYCL FP16)
Android:
- Android arm64 (CPU)
Windows:
- Windows x64 (CPU)
- Windows arm64 (CPU)
- Windows x64 (CUDA 12) - CUDA 12.4 DLLs
- Windows x64 (CUDA 13) - CUDA 13.1 DLLs
- Windows x64 (Vulkan)
- Windows x64 (SYCL)
- Windows x64 (HIP)
openEuler:
- openEuler x86 (310p)
- openEuler x86 (910b, ACL Graph)
- openEuler aarch64 (310p)
- openEuler aarch64 (910b, ACL Graph)

ggml-webgpu: add layer norm ops (#22406)
- shader(norm): add layer norm ops
- shader(norm): stablize floating point computation with Kahan summation and handle mixed types
- shader(norm): remove the non-contiguous strides
- shader(norm): use the original implementation rather than the kahan summation
macOS/iOS:
- macOS Apple Silicon (arm64)
- macOS Apple Silicon (arm64, KleidiAI enabled)
- macOS Intel (x64)
- iOS XCFramework
Linux:
- Ubuntu x64 (CPU)
- Ubuntu arm64 (CPU)
- Ubuntu s390x (CPU)
- Ubuntu x64 (Vulkan)
- Ubuntu arm64 (Vulkan)
- Ubuntu x64 (ROCm 7.2)
- Ubuntu x64 (OpenVINO)
- Ubuntu x64 (SYCL FP32)
- Ubuntu x64 (SYCL FP16)
Android:
- Android arm64 (CPU)
Windows:
- Windows x64 (CPU)
- Windows arm64 (CPU)
- Windows x64 (CUDA 12) - CUDA 12.4 DLLs
- Windows x64 (CUDA 13) - CUDA 13.1 DLLs
- Windows x64 (Vulkan)
- Windows x64 (SYCL)
- Windows x64 (HIP)
openEuler:
- openEuler x86 (310p)
- openEuler x86 (910b, ACL Graph)
- openEuler aarch64 (310p)
- openEuler aarch64 (910b, ACL Graph)

fix: CUDA device PCI bus ID de-dupe OOMing (ignoring other 3 gpus entirely) (#22533)
- fix: CUDA device PCI bus ID detection for multi-GPU de-dupe
- HIP, MUSA macros
Co-authored-by: Johannes Gäßler johannesg@5d6.de
macOS/iOS:
- macOS Apple Silicon (arm64)
- macOS Apple Silicon (arm64, KleidiAI enabled)
- macOS Intel (x64)
- iOS XCFramework
Linux:
- Ubuntu x64 (CPU)
- Ubuntu arm64 (CPU)
- Ubuntu s390x (CPU)
- Ubuntu x64 (Vulkan)
- Ubuntu arm64 (Vulkan)
- Ubuntu x64 (ROCm 7.2)
- Ubuntu x64 (OpenVINO)
- Ubuntu x64 (SYCL FP32)
- Ubuntu x64 (SYCL FP16)
Android:
- Android arm64 (CPU)
Windows:
- Windows x64 (CPU)
- Windows arm64 (CPU)
- Windows x64 (CUDA 12) - CUDA 12.4 DLLs
- Windows x64 (CUDA 13) - CUDA 13.1 DLLs
- Windows x64 (Vulkan)
- Windows x64 (SYCL)
- Windows x64 (HIP)
openEuler:
- openEuler x86 (310p)
- openEuler x86 (910b, ACL Graph)
- openEuler aarch64 (310p)
- openEuler aarch64 (910b, ACL Graph)

sync : ggml
macOS/iOS:
- macOS Apple Silicon (arm64)
- macOS Apple Silicon (arm64, KleidiAI enabled)
- macOS Intel (x64)
- iOS XCFramework
Linux:
- Ubuntu x64 (CPU)
- Ubuntu arm64 (CPU)
- Ubuntu s390x (CPU)
- Ubuntu x64 (Vulkan)
- Ubuntu arm64 (Vulkan)
- Ubuntu x64 (ROCm 7.2)
- Ubuntu x64 (OpenVINO)
- Ubuntu x64 (SYCL FP32)
- Ubuntu x64 (SYCL FP16)
Android:
- Android arm64 (CPU)
Windows:
- Windows x64 (CPU)
- Windows arm64 (CPU)
- Windows x64 (CUDA 12) - CUDA 12.4 DLLs
- Windows x64 (CUDA 13) - CUDA 13.1 DLLs
- Windows x64 (Vulkan)
- Windows x64 (SYCL)
- Windows x64 (HIP)
openEuler:
- openEuler x86 (310p)
- openEuler x86 (910b, ACL Graph)
- openEuler aarch64 (310p)
- openEuler aarch64 (910b, ACL Graph)

ggml-webgpu: add the upscale shader (#22419)
- shader(upscale): add the upscale shader with nearest, bilinear and bicubic implementations
- shader(upscale): use macro
macOS/iOS:
- macOS Apple Silicon (arm64)
- macOS Apple Silicon (arm64, KleidiAI enabled)
- macOS Intel (x64)
- iOS XCFramework
Linux:
- Ubuntu x64 (CPU)
- Ubuntu arm64 (CPU)
- Ubuntu s390x (CPU)
- Ubuntu x64 (Vulkan)
- Ubuntu arm64 (Vulkan)
- Ubuntu x64 (ROCm 7.2)
- Ubuntu x64 (OpenVINO)
- Ubuntu x64 (SYCL FP32)
- Ubuntu x64 (SYCL FP16)
Android:
- Android arm64 (CPU)
Windows:
- Windows x64 (CPU)
- Windows arm64 (CPU)
- Windows x64 (CUDA 12) - CUDA 12.4 DLLs
- Windows x64 (CUDA 13) - CUDA 13.1 DLLs
- Windows x64 (Vulkan)
- Windows x64 (SYCL)
- Windows x64 (HIP)
openEuler:
- openEuler x86 (310p)
- openEuler x86 (910b, ACL Graph)
- openEuler aarch64 (310p)
- openEuler aarch64 (910b, ACL Graph)

common : do not pass prompt tokens to reasoning budget sampler (#22488)
macOS/iOS:
- macOS Apple Silicon (arm64)
- macOS Apple Silicon (arm64, KleidiAI enabled)
- macOS Intel (x64)
- iOS XCFramework
Linux:
- Ubuntu x64 (CPU)
- Ubuntu arm64 (CPU)
- Ubuntu s390x (CPU)
- Ubuntu x64 (Vulkan)
- Ubuntu arm64 (Vulkan)
- Ubuntu x64 (ROCm 7.2)
- Ubuntu x64 (OpenVINO)
- Ubuntu x64 (SYCL FP32)
- Ubuntu x64 (SYCL FP16)
Android:
- Android arm64 (CPU)
Windows:
- Windows x64 (CPU)
- Windows arm64 (CPU)
- Windows x64 (CUDA 12) - CUDA 12.4 DLLs
- Windows x64 (CUDA 13) - CUDA 13.1 DLLs
- Windows x64 (Vulkan)
- Windows x64 (SYCL)
- Windows x64 (HIP)
openEuler:
- openEuler x86 (310p)
- openEuler x86 (910b, ACL Graph)
- openEuler aarch64 (310p)
- openEuler aarch64 (910b, ACL Graph)

ggml-cuda: add flash-attn support for DKQ=320/DV=256 with ncols2=32 (… (#22286)
- ggml-cuda: add flash-attn support for DKQ=320/DV=256 with ncols2=32 (GQA=32)
Adds MMA-f16 and tile kernel configs, dispatch logic, template instances,
and tile .cu file for Mistral Small 4 (head sizes 320/256), restricting to
ncols2=32 to support GQA ratio 32 only.
- Adding check to return BEST_FATTN_KERNEL_NONE in case GQA!=32
- Apply suggestions from code review
Address review comments
Co-authored-by: Johannes Gäßler johannesg@5d6.de
- Address review comments and making kernel config default to DQK=512, DV=512 instead of DQK=256,DV=256
- Fixed bug with sinks=1, with ncols=32, there are two warp-groups created but sinks index is same(0,...,15) for both the groups hence with sinks=1, output is not matching with CPU output. Added sink_base which will be base index for each warp_group (threadIdx.y / np)
- Apply suggestions from code review
Co-authored-by: Johannes Gäßler johannesg@5d6.de
- Update ggml/src/ggml-cuda/template-instances/generate_cu_files.py
Co-authored-by: Johannes Gäßler johannesg@5d6.de
Co-authored-by: Johannes Gäßler johannesg@5d6.de
macOS/iOS:
- macOS Apple Silicon (arm64)
- macOS Apple Silicon (arm64, KleidiAI enabled)
- macOS Intel (x64)
- iOS XCFramework
Linux:
- Ubuntu x64 (CPU)
- Ubuntu arm64 (CPU)
- Ubuntu s390x (CPU)
- Ubuntu x64 (Vulkan)
- Ubuntu arm64 (Vulkan)
- Ubuntu x64 (ROCm 7.2)
- Ubuntu x64 (OpenVINO)
- Ubuntu x64 (SYCL FP32)
- Ubuntu x64 (SYCL FP16)
Android:
- Android arm64 (CPU)
Windows:
- Windows x64 (CPU)
- Windows arm64 (CPU)
- Windows x64 (CUDA 12) - CUDA 12.4 DLLs
- Windows x64 (CUDA 13) - CUDA 13.1 DLLs
- Windows x64 (Vulkan)
- Windows x64 (SYCL)
- Windows x64 (HIP)
openEuler:
- openEuler x86 (310p)
- openEuler x86 (910b, ACL Graph)
- openEuler aarch64 (310p)
- openEuler aarch64 (910b, ACL Graph)

ggml-webgpu: add Q1_0 support (#22374)
- add fast matmul matvec q1_0 kernel
- ggml-webgpu: drop redundant zero-fills in Q1_0 shmem init
macOS/iOS:
- macOS Apple Silicon (arm64)
- macOS Apple Silicon (arm64, KleidiAI enabled)
- macOS Intel (x64)
- iOS XCFramework
Linux:
- Ubuntu x64 (CPU)
- Ubuntu arm64 (CPU)
- Ubuntu s390x (CPU)
- Ubuntu x64 (Vulkan)
- Ubuntu arm64 (Vulkan)
- Ubuntu x64 (ROCm 7.2)
- Ubuntu x64 (OpenVINO)
- Ubuntu x64 (SYCL FP32)
- Ubuntu x64 (SYCL FP16)
Android:
- Android arm64 (CPU)
Windows:
- Windows x64 (CPU)
- Windows arm64 (CPU)
- Windows x64 (CUDA 12) - CUDA 12.4 DLLs
- Windows x64 (CUDA 13) - CUDA 13.1 DLLs
- Windows x64 (Vulkan)
- Windows x64 (SYCL)
- Windows x64 (HIP)
openEuler:
- openEuler x86 (310p)
- openEuler x86 (910b, ACL Graph)
- openEuler aarch64 (310p)
- openEuler aarch64 (910b, ACL Graph)

common: fix missing exports in llama-common (#22340)
- common: refactor common/debug to move abort_on_nan into base_callback_data
Passing bool abort_on_nan as template parameter for common_debug_cb_eval is unnecessary and creates an issue with LTO.
It should just be a member of the base_callback_data instead.
- cont : cleanup
- common : use pimpl in debug.h to reduce header dependencies
Move common_debug_cb_user_data's data members (std::regex,
std::vector<uint8_t>) into a private impl struct in debug.cpp.
This removes the includes of common.h and from debug.h,
reducing transitive dependencies for any translation unit that
includes the header.
Assisted-by: llama.cpp:local pi
Co-authored-by: Georgi Gerganov ggerganov@gmail.com
macOS/iOS:
- macOS Apple Silicon (arm64)
- macOS Apple Silicon (arm64, KleidiAI enabled)
- macOS Intel (x64)
- iOS XCFramework
Linux:
- Ubuntu x64 (CPU)
- Ubuntu arm64 (CPU)
- Ubuntu s390x (CPU)
- Ubuntu x64 (Vulkan)
- Ubuntu arm64 (Vulkan)
- Ubuntu x64 (ROCm 7.2)
- Ubuntu x64 (OpenVINO)
- Ubuntu x64 (SYCL FP32)
- Ubuntu x64 (SYCL FP16)
Android:
- Android arm64 (CPU)
Windows:
- Windows x64 (CPU)
- Windows arm64 (CPU)
- Windows x64 (CUDA 12) - CUDA 12.4 DLLs
- Windows x64 (CUDA 13) - CUDA 13.1 DLLs
- Windows x64 (Vulkan)
- Windows x64 (SYCL)
- Windows x64 (HIP)
openEuler:
- openEuler x86 (310p)
- openEuler x86 (910b, ACL Graph)
- openEuler aarch64 (310p)
- openEuler aarch64 (910b, ACL Graph)

hexagon: guard HMX clock request for v75+ platforms (#22377)
macOS/iOS:
- macOS Apple Silicon (arm64)
- macOS Apple Silicon (arm64, KleidiAI enabled)
- macOS Intel (x64)
- iOS XCFramework
Linux:
- Ubuntu x64 (CPU)
- Ubuntu arm64 (CPU)
- Ubuntu s390x (CPU)
- Ubuntu x64 (Vulkan)
- Ubuntu arm64 (Vulkan)
- Ubuntu x64 (ROCm 7.2)
- Ubuntu x64 (OpenVINO)
- Ubuntu x64 (SYCL FP32)
- Ubuntu x64 (SYCL FP16)
Android:
- Android arm64 (CPU)
Windows:
- Windows x64 (CPU)
- Windows arm64 (CPU)
- Windows x64 (CUDA 12) - CUDA 12.4 DLLs
- Windows x64 (CUDA 13) - CUDA 13.1 DLLs
- Windows x64 (Vulkan)
- Windows x64 (SYCL)
- Windows x64 (HIP)
openEuler:
- openEuler x86 (310p)
- openEuler x86 (910b, ACL Graph)
- openEuler aarch64 (310p)
- openEuler aarch64 (910b, ACL Graph)

parser: fix structured output bug (#22302)
- fix very stupid structured output bug
- Things just cannot be too easy.
macOS/iOS:
- macOS Apple Silicon (arm64)
- macOS Apple Silicon (arm64, KleidiAI enabled)
- macOS Intel (x64)
- iOS XCFramework
Linux:
- Ubuntu x64 (CPU)
- Ubuntu arm64 (CPU)
- Ubuntu s390x (CPU)
- Ubuntu x64 (Vulkan)
- Ubuntu arm64 (Vulkan)
- Ubuntu x64 (ROCm 7.2)
- Ubuntu x64 (OpenVINO)
- Ubuntu x64 (SYCL FP32)
- Ubuntu x64 (SYCL FP16)
Android:
- Android arm64 (CPU)
Windows:
- Windows x64 (CPU)
- Windows arm64 (CPU)
- Windows x64 (CUDA 12) - CUDA 12.4 DLLs
- Windows x64 (CUDA 13) - CUDA 13.1 DLLs
- Windows x64 (Vulkan)
- Windows x64 (SYCL)
- Windows x64 (HIP)
openEuler:
- openEuler x86 (310p)
- openEuler x86 (910b, ACL Graph)
- openEuler aarch64 (310p)
- openEuler aarch64 (910b, ACL Graph)

fix(shader): handle the buffer aliasing for rms fuse (#22266)
macOS/iOS:
- macOS Apple Silicon (arm64)
- macOS Apple Silicon (arm64, KleidiAI enabled)
- macOS Intel (x64)
- iOS XCFramework
Linux:
- Ubuntu x64 (CPU)
- Ubuntu arm64 (CPU)
- Ubuntu s390x (CPU)
- Ubuntu x64 (Vulkan)
- Ubuntu arm64 (Vulkan)
- Ubuntu x64 (ROCm 7.2)
- Ubuntu x64 (OpenVINO)
- Ubuntu x64 (SYCL FP32)
- Ubuntu x64 (SYCL FP16)
Android:
- Android arm64 (CPU)
Windows:
- Windows x64 (CPU)
- Windows arm64 (CPU)
- Windows x64 (CUDA 12) - CUDA 12.4 DLLs
- Windows x64 (CUDA 13) - CUDA 13.1 DLLs
- Windows x64 (Vulkan)
- Windows x64 (SYCL)
- Windows x64 (HIP)
openEuler:
- openEuler x86 (310p)
- openEuler x86 (910b, ACL Graph)
- openEuler aarch64 (310p)
- openEuler aarch64 (910b, ACL Graph)

HIP: flip GGML_HIP_GRAPHS to default on (#22254)
In #11362 hip graph was disabled by default as, at the time, its performance impact was negative. Due to improvements in rocm and our usage and construction of graphs this is no longer true, so lets change the default.
macOS/iOS:
- macOS Apple Silicon (arm64)
- macOS Apple Silicon (arm64, KleidiAI enabled)
- macOS Intel (x64)
- iOS XCFramework
Linux:
- Ubuntu x64 (CPU)
- Ubuntu arm64 (CPU)
- Ubuntu s390x (CPU)
- Ubuntu x64 (Vulkan)
- Ubuntu arm64 (Vulkan)
- Ubuntu x64 (ROCm 7.2)
- Ubuntu x64 (OpenVINO)
Android:
- Android arm64 (CPU)
Windows:
- Windows x64 (CPU)
- Windows arm64 (CPU)
- Windows x64 (CUDA 12) - CUDA 12.4 DLLs
- Windows x64 (CUDA 13) - CUDA 13.1 DLLs
- Windows x64 (Vulkan)
- Windows x64 (SYCL)
- Windows x64 (HIP)
openEuler:
- openEuler x86 (310p)
- openEuler x86 (910b, ACL Graph)
- openEuler aarch64 (310p)
- openEuler aarch64 (910b, ACL Graph)

ggml-webgpu(shader): support conv2d kernels. (#21964)
- ggml(webgpu): fix the busy-polls in Emscripten in the waitAny after #20618, and remove the busy webgpu log
- Merge with upstream
- Fix GET_ROWS packed integer NaN when using f16 as memory buffer in shader quants
- Update Unary wgsl EXP and EXPM1 for f16 stability
- Fix GET_ROWS IQ4_XS strcut for NaN f16 canonicalization
- Fix numerical percision for unary sqrt when working with f16
- Fix NaN canonicalization for packed integers using f16
- Update err threshold for binary div ops when using f16
- backend: Keep one Dawn/WebGPU instance alive for the lifetime of the static backend
- clean: uncomment existing code logs
- clean: clean the unncessary debug info
- Refactor and generalize dequant helpers
- Remove deprecated quant structs
- Refactor shader defines to reduce repetition
- Remove error override for F16 type
- fix: fix the accidential removal of the proper initialization of ctx
- clean: clean legacy and format code
- fix: did not modify tests ops
- shader(conv2d): add conv2d shader kernels and pass f32 and f16 tests
- shader(conv2d): fix the out of bounds memory access in the weight indexing
- shader(conv2d): clean unused variables and optimize the computation
- merge: use the new entries function
- clean: address the formatting issues
- clean: address the warning issues
- clear: clean the shader editorconfig-checker issues
- clear: clean the shader editorconfig-checker with utf-8
Co-authored-by: Jeremy J. Hartmann jeremy@mtion.tv
macOS/iOS:
- macOS Apple Silicon (arm64)
- macOS Apple Silicon (arm64, KleidiAI enabled)
- macOS Intel (x64)
- iOS XCFramework
Linux:
- Ubuntu x64 (CPU)
- Ubuntu arm64 (CPU)
- Ubuntu s390x (CPU)
- Ubuntu x64 (Vulkan)
- Ubuntu arm64 (Vulkan)
- Ubuntu x64 (ROCm 7.2)
- Ubuntu x64 (OpenVINO)
Android:
- Android arm64 (CPU)
Windows:
- Windows x64 (CPU)
- Windows arm64 (CPU)
- Windows x64 (CUDA 12) - CUDA 12.4 DLLs
- Windows x64 (CUDA 13) - CUDA 13.1 DLLs
- Windows x64 (Vulkan)
- Windows x64 (SYCL)
- Windows x64 (HIP)
openEuler:
- openEuler x86 (310p)
- openEuler x86 (910b, ACL Graph)
- openEuler aarch64 (310p)
- openEuler aarch64 (910b, ACL Graph)

server : fix hardcoded proxy connection timeout in router mode (#18760) (#22003)
Fixes: #18760
Co-authored-by: Christian christian@example.com
macOS/iOS:
- macOS Apple Silicon (arm64)
- macOS Apple Silicon (arm64, KleidiAI enabled)
- macOS Intel (x64)
- iOS XCFramework
Linux:
- Ubuntu x64 (CPU)
- Ubuntu arm64 (CPU)
- Ubuntu s390x (CPU)
- Ubuntu x64 (Vulkan)
- Ubuntu arm64 (Vulkan)
- Ubuntu x64 (ROCm 7.2)
- Ubuntu x64 (OpenVINO)
Android:
- Android arm64 (CPU)
Windows:
- Windows x64 (CPU)
- Windows arm64 (CPU)
- Windows x64 (CUDA 12) - CUDA 12.4 DLLs
- Windows x64 (CUDA 13) - CUDA 13.1 DLLs
- Windows x64 (Vulkan)
- Windows x64 (SYCL)
- Windows x64 (HIP)
openEuler:
- openEuler x86 (310p)
- openEuler x86 (910b, ACL Graph)
- openEuler aarch64 (310p)
- openEuler aarch64 (910b, ACL Graph)

vendor : update cpp-httplib to 0.42.0 (#21781)
macOS/iOS:
- macOS Apple Silicon (arm64)
- macOS Apple Silicon (arm64, KleidiAI enabled)
- macOS Intel (x64)
- iOS XCFramework
Linux:
- Ubuntu x64 (CPU)
- Ubuntu arm64 (CPU)
- Ubuntu s390x (CPU)
- Ubuntu x64 (Vulkan)
- Ubuntu arm64 (Vulkan)
- Ubuntu x64 (ROCm 7.2)
- Ubuntu x64 (OpenVINO)
Android:
- Android arm64 (CPU)
Windows:
- Windows x64 (CPU)
- Windows arm64 (CPU)
- Windows x64 (CUDA 12) - CUDA 12.4 DLLs
- Windows x64 (CUDA 13) - CUDA 13.1 DLLs
- Windows x64 (Vulkan)
- Windows x64 (SYCL)
- Windows x64 (HIP)
openEuler:
- openEuler x86 (310p)
- openEuler x86 (910b, ACL Graph)
- openEuler aarch64 (310p)
- openEuler aarch64 (910b, ACL Graph)

server: Expose media_tag on /props endpoint. (#22028)
macOS/iOS:
- macOS Apple Silicon (arm64)
- macOS Apple Silicon (arm64, KleidiAI enabled)
- macOS Intel (x64)
- iOS XCFramework
Linux:
- Ubuntu x64 (CPU)
- Ubuntu arm64 (CPU)
- Ubuntu s390x (CPU)
- Ubuntu x64 (Vulkan)
- Ubuntu arm64 (Vulkan)
- Ubuntu x64 (ROCm 7.2)
- Ubuntu x64 (OpenVINO)
Android:
- Android arm64 (CPU)
Windows:
- Windows x64 (CPU)
- Windows arm64 (CPU)
- Windows x64 (CUDA 12) - CUDA 12.4 DLLs
- Windows x64 (CUDA 13) - CUDA 13.1 DLLs
- Windows x64 (Vulkan)
- Windows x64 (SYCL)
- Windows x64 (HIP)
openEuler:
- openEuler x86 (310p)
- openEuler x86 (910b, ACL Graph)
- openEuler aarch64 (310p)
- openEuler aarch64 (910b, ACL Graph)

ggml-webgpu: fix compiler warnings and refactor FlashAttention encoding (#21052)
- Update workflows to remove dependence on llvmpipe
- Try setting Dawn_DIR
- remove c++20 initializers
- Move to proper guid
- Try avoiding segfaults on vulkan backend process exit
- Remove compiler warnings on parameter casting
- Fix soft_max and update reg_tile accumulation to f32 for better precision
- Refactor flash_attn a bit
- remove c++20 initializers and format
- Increase div precision for NVIDIA
- revert div precision and comment out ggml-ci node for now
- Formatting
- Try debugging on a failing CI node
- Revert "Try debugging on a failing CI node"
This reverts commit 1971e33.
macOS/iOS:
- macOS Apple Silicon (arm64)
- macOS Apple Silicon (arm64, KleidiAI enabled)
- macOS Intel (x64)
- iOS XCFramework
Linux:
- Ubuntu x64 (CPU)
- Ubuntu arm64 (CPU)
- Ubuntu s390x (CPU)
- Ubuntu x64 (Vulkan)
- Ubuntu arm64 (Vulkan)
- Ubuntu x64 (ROCm 7.2)
- Ubuntu x64 (OpenVINO)
Android:
- Android arm64 (CPU)
Windows:
- Windows x64 (CPU)
- Windows arm64 (CPU)
- Windows x64 (CUDA 12) - CUDA 12.4 DLLs
- Windows x64 (CUDA 13) - CUDA 13.1 DLLs
- Windows x64 (Vulkan)
- Windows x64 (SYCL)
- Windows x64 (HIP)
openEuler:
- openEuler x86 (310p)
- openEuler x86 (910b, ACL Graph)
- openEuler aarch64 (310p)
- openEuler aarch64 (910b, ACL Graph)

cli : use get_media_marker (#22017)
macOS/iOS:
- macOS Apple Silicon (arm64)
- macOS Apple Silicon (arm64, KleidiAI enabled)
- macOS Intel (x64)
- iOS XCFramework
Linux:
- Ubuntu x64 (CPU)
- Ubuntu arm64 (CPU)
- Ubuntu s390x (CPU)
- Ubuntu x64 (Vulkan)
- Ubuntu arm64 (Vulkan)
- Ubuntu x64 (ROCm 7.2)
- Ubuntu x64 (OpenVINO)
Windows:
- Windows x64 (CPU)
- Windows arm64 (CPU)
- Windows x64 (CUDA 12) - CUDA 12.4 DLLs
- Windows x64 (CUDA 13) - CUDA 13.1 DLLs
- Windows x64 (Vulkan)
- Windows x64 (SYCL)
- Windows x64 (HIP)
openEuler:
- openEuler x86 (310p)
- openEuler x86 (910b, ACL Graph)
- openEuler aarch64 (310p)
- openEuler aarch64 (910b, ACL Graph)

server: use random media marker (#21962)
- server: use random media marker
- nits
- remove legacy <image> token
- revert special char in random
macOS/iOS:
- macOS Apple Silicon (arm64)
- macOS Apple Silicon (arm64, KleidiAI enabled)
- macOS Intel (x64)
- iOS XCFramework
Linux:
- Ubuntu x64 (CPU)
- Ubuntu arm64 (CPU)
- Ubuntu s390x (CPU)
- Ubuntu x64 (Vulkan)
- Ubuntu arm64 (Vulkan)
- Ubuntu x64 (ROCm 7.2)
- Ubuntu x64 (OpenVINO)
Windows:
- Windows x64 (CPU)
- Windows arm64 (CPU)
- Windows x64 (CUDA 12) - CUDA 12.4 DLLs
- Windows x64 (CUDA 13) - CUDA 13.1 DLLs
- Windows x64 (Vulkan)
- Windows x64 (SYCL)
- Windows x64 (HIP)
openEuler:
- openEuler x86 (310p)
- openEuler x86 (910b, ACL Graph)
- openEuler aarch64 (310p)
- openEuler aarch64 (910b, ACL Graph)

CUDA: also store node->src ne/nb for graph equality (#21736)
macOS/iOS:
- macOS Apple Silicon (arm64)
- macOS Apple Silicon (arm64, KleidiAI enabled)
- macOS Intel (x64)
- iOS XCFramework
Linux:
- Ubuntu x64 (CPU)
- Ubuntu arm64 (CPU)
- Ubuntu s390x (CPU)
- Ubuntu x64 (Vulkan)
- Ubuntu arm64 (Vulkan)
- Ubuntu x64 (ROCm 7.2)
- Ubuntu x64 (OpenVINO)
Windows:
- Windows x64 (CPU)
- Windows arm64 (CPU)
- Windows x64 (CUDA 12) - CUDA 12.4 DLLs
- Windows x64 (CUDA 13) - CUDA 13.1 DLLs
- Windows x64 (Vulkan)
- Windows x64 (SYCL)
- Windows x64 (HIP)
openEuler:
- openEuler x86 (310p)
- openEuler x86 (910b, ACL Graph)
- openEuler aarch64 (310p)
- openEuler aarch64 (910b, ACL Graph)

CUDA: fuse muls (#21665)
macOS/iOS:
- macOS Apple Silicon (arm64)
- macOS Apple Silicon (arm64, KleidiAI enabled)
- macOS Intel (x64)
- iOS XCFramework
Linux:
- Ubuntu x64 (CPU)
- Ubuntu arm64 (CPU)
- Ubuntu s390x (CPU)
- Ubuntu x64 (Vulkan)
- Ubuntu arm64 (Vulkan)
- Ubuntu x64 (ROCm 7.2)
- Ubuntu x64 (OpenVINO)
Windows:
- Windows x64 (CPU)
- Windows arm64 (CPU)
- Windows x64 (CUDA 12) - CUDA 12.4 DLLs
- Windows x64 (CUDA 13) - CUDA 13.1 DLLs
- Windows x64 (Vulkan)
- Windows x64 (SYCL)
- Windows x64 (HIP)
openEuler:
- openEuler x86 (310p)
- openEuler x86 (910b, ACL Graph)
- openEuler aarch64 (310p)
- openEuler aarch64 (910b, ACL Graph)

CUDA: also store node->src->data ptrs for equality check (#21635)
- CUDA: also store node->src->data ptrs for equality check
- address review comments
macOS/iOS:
- macOS Apple Silicon (arm64)
- macOS Apple Silicon (arm64, KleidiAI enabled)
- macOS Intel (x64)
- iOS XCFramework
Linux:
- Ubuntu x64 (CPU)
- Ubuntu arm64 (CPU)
- Ubuntu s390x (CPU)
- Ubuntu x64 (Vulkan)
- Ubuntu arm64 (Vulkan)
- Ubuntu x64 (ROCm 7.2)
- Ubuntu x64 (OpenVINO)
Windows:
- Windows x64 (CPU)
- Windows arm64 (CPU)
- Windows x64 (CUDA 12) - CUDA 12.4 DLLs
- Windows x64 (CUDA 13) - CUDA 13.1 DLLs
- Windows x64 (Vulkan)
- Windows x64 (SYCL)
- Windows x64 (HIP)
openEuler:
- openEuler x86 (310p)
- openEuler x86 (910b, ACL Graph)
- openEuler aarch64 (310p)
- openEuler aarch64 (910b, ACL Graph)

devops: kleidiai: provide KleidiAI-Enabled ARM Release Artifact (#21259)
- Unified macOS release setup with strategy-matrix block
- Added KleidiAI arm64 macOS release definition
Change-Id: I05520889ffc646488a178d06817a17f29274465a
Signed-off-by: Martin Klacer martin.klacer@arm.com
macOS/iOS:
- macOS Apple Silicon (arm64)
- macOS Apple Silicon (arm64, KleidiAI enabled)
- macOS Intel (x64)
- iOS XCFramework
Linux:
- Ubuntu x64 (CPU)
- Ubuntu arm64 (CPU)
- Ubuntu s390x (CPU)
- Ubuntu x64 (Vulkan)
- Ubuntu arm64 (Vulkan)
- Ubuntu x64 (ROCm 7.2)
- Ubuntu x64 (OpenVINO)
Windows:
- Windows x64 (CPU)
- Windows arm64 (CPU)
- Windows x64 (CUDA 12) - CUDA 12.4 DLLs
- Windows x64 (CUDA 13) - CUDA 13.1 DLLs
- Windows x64 (Vulkan)
- Windows x64 (SYCL)
- Windows x64 (HIP)
openEuler:
- openEuler x86 (310p)
- openEuler x86 (910b, ACL Graph)
- openEuler aarch64 (310p)
- openEuler aarch64 (910b, ACL Graph)

ggml-webgpu: Add the support of MUL_MAT_ID (#21147)
- Add mul_mat_id support to WebGPU
- Apply suggestion from @reeselevine
Co-authored-by: Reese Levine reeselevine1@gmail.com
macOS/iOS:
- macOS Apple Silicon (arm64)
- macOS Intel (x64)
- iOS XCFramework
Linux:
- Ubuntu x64 (CPU)
- Ubuntu arm64 (CPU)
- Ubuntu s390x (CPU)
- Ubuntu x64 (Vulkan)
- Ubuntu arm64 (Vulkan)
- Ubuntu x64 (ROCm 7.2)
- Ubuntu x64 (OpenVINO)
Windows:
- Windows x64 (CPU)
- Windows arm64 (CPU)
- Windows x64 (CUDA 12) - CUDA 12.4 DLLs
- Windows x64 (CUDA 13) - CUDA 13.1 DLLs
- Windows x64 (Vulkan)
- Windows x64 (SYCL)
- Windows x64 (HIP)
openEuler:
- openEuler x86 (310p)
- openEuler x86 (910b, ACL Graph)
- openEuler aarch64 (310p)
- openEuler aarch64 (910b, ACL Graph)

hexagon: slight optimization for argosrt output init (#21463)
macOS/iOS:
- macOS Apple Silicon (arm64)
- macOS Intel (x64)
- iOS XCFramework
Linux:
- Ubuntu x64 (CPU)
- Ubuntu arm64 (CPU)
- Ubuntu s390x (CPU)
- Ubuntu x64 (Vulkan)
- Ubuntu arm64 (Vulkan)
- Ubuntu x64 (ROCm 7.2)
- Ubuntu x64 (OpenVINO)
Windows:
- Windows x64 (CPU)
- Windows arm64 (CPU)
- Windows x64 (CUDA 12) - CUDA 12.4 DLLs
- Windows x64 (CUDA 13) - CUDA 13.1 DLLs
- Windows x64 (Vulkan)
- Windows x64 (SYCL)
- Windows x64 (HIP)
openEuler:
- openEuler x86 (310p)
- openEuler x86 (910b, ACL Graph)
- openEuler aarch64 (310p)
- openEuler aarch64 (910b, ACL Graph)

common : add gemma 4 specialized parser (#21418)
- common : add gemma4 dedicated parser
- cont : add '<|tool_response>' as eog
- cont : emit JSON from Gemma4 tool call AST
- cont : more fixes
- cont : refactor convert function
- cont : refine rules and mapping
- cont : add more tests
- cont : clean up
- cont : remove autoparser gemma4 implementation
- cont : more cleanup
- cont : rename gemma4.jinja to match the others
- cont : add custom template to support interleaved thinking
- cont : preserve reasoning in model turns
- cont : fix initializer error
- cont : fix unused vars
- cont : fix accidental static
- cont : fix specialized_template signature
- fix extra semicolon
- remove debug line and extra space [no ci]
macOS/iOS:
- macOS Apple Silicon (arm64)
- macOS Intel (x64)
- iOS XCFramework
Linux:
- Ubuntu x64 (CPU)
- Ubuntu arm64 (CPU)
- Ubuntu s390x (CPU)
- Ubuntu x64 (Vulkan)
- Ubuntu arm64 (Vulkan)
- Ubuntu x64 (ROCm 7.2)
- Ubuntu x64 (OpenVINO)
Windows:
- Windows x64 (CPU)
- Windows arm64 (CPU)
- Windows x64 (CUDA 12) - CUDA 12.4 DLLs
- Windows x64 (CUDA 13) - CUDA 13.1 DLLs
- Windows x64 (Vulkan)
- Windows x64 (SYCL)
- Windows x64 (HIP)
openEuler:
- openEuler x86 (310p)
- openEuler x86 (910b, ACL Graph)
- openEuler aarch64 (310p)
- openEuler aarch64 (910b, ACL Graph)

ggml-webgpu: move from parameter buffer pool to single buffer with offsets (#21278)
- Work towards removing bitcast
- Move rest of existing types over
- Add timeout back to wait and remove synchronous set_tensor/memset_tensor
- move to unpackf16 for wider compatibility
- cleanup
- Remove deadlock condition in free_bufs
- Start work on removing parameter buffer pools
- Simplify and optimize further
- simplify profile futures
- Fix stride
- Try using a single command buffer per batch
- formatting
macOS/iOS:
- macOS Apple Silicon (arm64)
- macOS Intel (x64)
- iOS XCFramework
Linux:
- Ubuntu x64 (CPU)
- Ubuntu arm64 (CPU)
- Ubuntu s390x (CPU)
- Ubuntu x64 (Vulkan)
- Ubuntu arm64 (Vulkan)
- Ubuntu x64 (ROCm 7.2)
- Ubuntu x64 (OpenVINO)
Windows:
- Windows x64 (CPU)
- Windows arm64 (CPU)
- Windows x64 (CUDA 12) - CUDA 12.4 DLLs
- Windows x64 (CUDA 13) - CUDA 13.1 DLLs
- Windows x64 (Vulkan)
- Windows x64 (SYCL)
- Windows x64 (HIP)
openEuler:
- openEuler x86 (310p)
- openEuler x86 (910b, ACL Graph)
- openEuler aarch64 (310p)
- openEuler aarch64 (910b, ACL Graph)

[HIP] Bump ROCm version to 7.2.1 (#21066)
Bump ROCm version on Linux from 7.2 to 7.2.1
Add gfx1102 target
Delete LLVM workaround since ROCm 7.2.1 has fix for ROCm 7.2 perf regression ROCm/rocm-systems#2865
Co-authored-by: Sigbjørn Skjæret sigbjorn.skjaeret@scala.com
macOS/iOS:
- macOS Apple Silicon (arm64)
- macOS Intel (x64)
- iOS XCFramework
Linux:
- Ubuntu x64 (CPU)
- Ubuntu arm64 (CPU)
- Ubuntu s390x (CPU)
- Ubuntu x64 (Vulkan)
- Ubuntu arm64 (Vulkan)
- Ubuntu x64 (ROCm 7.2)
- Ubuntu x64 (OpenVINO)
Windows:
- Windows x64 (CPU)
- Windows arm64 (CPU)
- Windows x64 (CUDA 12) - CUDA 12.4 DLLs
- Windows x64 (CUDA 13) - CUDA 13.1 DLLs
- Windows x64 (Vulkan)
- Windows x64 (SYCL)
- Windows x64 (HIP)
openEuler:
- openEuler x86 (310p)
- openEuler x86 (910b, ACL Graph)
- openEuler aarch64 (310p)
- openEuler aarch64 (910b, ACL Graph)

hexagon : add cumsum op support (#21246)
- hexagon : add cumsum op support
- hexagon: enable dma for cumsum op
- Fix line-ending
Co-authored-by: Max Krasnyansky maxk@qti.qualcomm.com
macOS/iOS:
- macOS Apple Silicon (arm64)
- macOS Intel (x64)
- iOS XCFramework
Linux:
- Ubuntu x64 (CPU)
- Ubuntu arm64 (CPU)
- Ubuntu s390x (CPU)
- Ubuntu x64 (Vulkan)
- Ubuntu arm64 (Vulkan)
- Ubuntu x64 (ROCm 7.2)
- Ubuntu x64 (OpenVINO)
Windows:
- Windows x64 (CPU)
- Windows arm64 (CPU)
- Windows x64 (CUDA 12) - CUDA 12.4 DLLs
- Windows x64 (CUDA 13) - CUDA 13.1 DLLs
- Windows x64 (Vulkan)
- Windows x64 (SYCL)
- Windows x64 (HIP)
openEuler:
- openEuler x86 (310p)
- openEuler x86 (910b, ACL Graph)
- openEuler aarch64 (310p)
- openEuler aarch64 (910b, ACL Graph)

ggml-webgpu: port all AOT operators to JIT (#20728)
- port cpy pipeline to shader lib with JIT compilation
- port glu pipeline to shader lib with JIT compilation
- port rope pipeline to shader lib with JIT compilation
- port soft_max pipeline to shader lib with JIT compilation
- removed unused functions from embed_wgsl.py which were used for
old AOT template expansion
macOS/iOS:
- macOS Apple Silicon (arm64)
- macOS Intel (x64)
- iOS XCFramework
Linux:
- Ubuntu x64 (CPU)
- Ubuntu arm64 (CPU)
- Ubuntu s390x (CPU)
- Ubuntu x64 (Vulkan)
- Ubuntu arm64 (Vulkan)
- Ubuntu x64 (ROCm 7.2)
- Ubuntu x64 (OpenVINO)
Windows:
- Windows x64 (CPU)
- Windows arm64 (CPU)
- Windows x64 (CUDA 12) - CUDA 12.4 DLLs
- Windows x64 (CUDA 13) - CUDA 13.1 DLLs
- Windows x64 (Vulkan)
- Windows x64 (SYCL)
- Windows x64 (HIP)
openEuler:
- openEuler x86 (310p)
- openEuler x86 (910b, ACL Graph)
- openEuler aarch64 (310p)
- openEuler aarch64 (910b, ACL Graph)

opencl: add q4_K gemm and gemv kernels for Adreno (#20919)
- opencl: add q4_K gemm and gemv kernels for Adreno
- opencl: fix whitespace
- opencl: add workarounds for compiler bugs on older devices
- opencl: handle fp16 denorm on X Elite
- opencl: fix kernel build error
- opencl: fix whitespace
- opencl: make q4_K cvt kernels signature consistent
Co-authored-by: Li He lih@qti.qualcomm.com
macOS/iOS:
- macOS Apple Silicon (arm64)
- macOS Intel (x64)
- iOS XCFramework
Linux:
- Ubuntu x64 (CPU)
- Ubuntu x64 (Vulkan)
- Ubuntu x64 (ROCm 7.2)
- Ubuntu s390x (CPU)
- Ubuntu x64 (OpenVINO)
Windows:
- Windows x64 (CPU)
- Windows arm64 (CPU)
- Windows x64 (CUDA 12) - CUDA 12.4 DLLs
- Windows x64 (CUDA 13) - CUDA 13.1 DLLs
- Windows x64 (Vulkan)
- Windows x64 (SYCL)
- Windows x64 (HIP)
openEuler:
- openEuler x86 (310p)
- openEuler x86 (910b, ACL Graph)
- openEuler aarch64 (310p)
- openEuler aarch64 (910b, ACL Graph)

fix **/x glob matching (#21129)
macOS/iOS:
- macOS Apple Silicon (arm64)
- macOS Intel (x64)
- iOS XCFramework
Linux:
- Ubuntu x64 (CPU)
- Ubuntu x64 (Vulkan)
- Ubuntu x64 (ROCm 7.2)
- Ubuntu s390x (CPU)
- Ubuntu x64 (OpenVINO)
Windows:
- Windows x64 (CPU)
- Windows arm64 (CPU)
- Windows x64 (CUDA 12) - CUDA 12.4 DLLs
- Windows x64 (CUDA 13) - CUDA 13.1 DLLs
- Windows x64 (Vulkan)
- Windows x64 (SYCL)
- Windows x64 (HIP)
openEuler:
- openEuler x86 (310p)
- openEuler x86 (910b, ACL Graph)
- openEuler aarch64 (310p)
- openEuler aarch64 (910b, ACL Graph)

cli : add /glob command (#21084)
- add /glob command
- output error when max files reached
- support globbing outside curdir
macOS/iOS:
- macOS Apple Silicon (arm64)
- macOS Intel (x64)
- iOS XCFramework
Linux:
- Ubuntu x64 (CPU)
- Ubuntu x64 (Vulkan)
- Ubuntu x64 (ROCm 7.2)
- Ubuntu s390x (CPU)
- Ubuntu x64 (OpenVINO)
Windows:
- Windows x64 (CPU)
- Windows arm64 (CPU)
- Windows x64 (CUDA 12) - CUDA 12.4 DLLs
- Windows x64 (CUDA 13) - CUDA 13.1 DLLs
- Windows x64 (Vulkan)
- Windows x64 (SYCL)
- Windows x64 (HIP)
openEuler:
- openEuler x86 (310p)
- openEuler x86 (910b, ACL Graph)
- openEuler aarch64 (310p)
- openEuler aarch64 (910b, ACL Graph)

CANN: update docker images to 8.5.0 and improve CANN.md (#20801)
- cann: update docker images to 8.5.0
- bump CANN base image from 8.3.rc2 to 8.5.0
- bump ASCEND_VERSION from 8.1.RC1.alpha001 to 8.5.0
Move to newer stable releases.
- cann: update CANN.md
- Update CANN.md to include BF16 support
Added BF16 support information to the CANN documentation and corrected formatting for the installation instructions.
- Fix formatting issues in CANN.md
Fix 234: Trailing whitespace
macOS/iOS:
- macOS Apple Silicon (arm64)
- macOS Intel (x64)
- iOS XCFramework
Linux:
- Ubuntu x64 (CPU)
- Ubuntu x64 (Vulkan)
- Ubuntu x64 (ROCm 7.2)
- Ubuntu s390x (CPU)
- Ubuntu x64 (OpenVINO)
Windows:
- Windows x64 (CPU)
- Windows arm64 (CPU)
- Windows x64 (CUDA 12) - CUDA 12.4 DLLs
- Windows x64 (CUDA 13) - CUDA 13.1 DLLs
- Windows x64 (Vulkan)
- Windows x64 (SYCL)
- Windows x64 (HIP)
openEuler:
- openEuler x86 (310p)
- openEuler x86 (910b, ACL Graph)
- openEuler aarch64 (310p)
- openEuler aarch64 (910b, ACL Graph)

CUDA & CPU: support F32 kernel type for CONV_TRANSPOSE_2D (#17094)
- Refactor CUDA 2D transpose implementation to support multiple kernel types and improve parameter handling
- Introduced a conv2d_transpose_params struct for better parameter management.
- Updated conv2d_transpose_kernel to be templated for different kernel types (float and half).
- Modified ggml_cuda_conv_2d_transpose_p0 to handle both F16 and F32 kernel types.
- Enhanced test cases to validate functionality for both kernel types.
- Refactor test cases for 2D convolution transpose to support dynamic kernel types
- Updated test_conv_transpose_2d structure to improve parameter handling by reordering constructor arguments.
- Enhanced test case generation to iterate over kernel types, allowing for flexible testing of different configurations.
- Removed hardcoded kernel type instances in favor of a loop for better maintainability and scalability.
- Refactor ggml_compute_forward_conv_transpose_2d to support both F16 and F32 tensor types.
- Refactor conv2d transpose kernel to use a template for kernel type, enhancing flexibility for different data types.
Update test cases to include both F16 and F32 tensor types for comprehensive coverage.
- Update ggml/src/ggml-cuda/conv2d-transpose.cu
Co-authored-by: Aman Gupta amangupta052@gmail.com
- Update ggml/src/ggml-cpu/ggml-cpu.c
Co-authored-by: Aman Gupta amangupta052@gmail.com
- Refactor conv2d transpose implementation by removing the conv2d_transpose_params struct and dispatching with direct kernel launch.
- Enhance cpu conv2d transpose implementation by introducing a templated kernel type for improved flexibility with F16 and F32 data types.
Co-authored-by: Aman Gupta amangupta052@gmail.com
macOS/iOS:
- macOS Apple Silicon (arm64)
- macOS Intel (x64)
- iOS XCFramework
Linux:
- Ubuntu x64 (CPU)
- Ubuntu x64 (Vulkan)
- Ubuntu x64 (ROCm 7.2)
- Ubuntu s390x (CPU)
- Ubuntu x64 (OpenVINO)
Windows:
- Windows x64 (CPU)
- Windows arm64 (CPU)
- Windows x64 (CUDA 12) - CUDA 12.4 DLLs
- Windows x64 (CUDA 13) - CUDA 13.1 DLLs
- Windows x64 (Vulkan)
- Windows x64 (SYCL)
- Windows x64 (HIP)
openEuler:
- openEuler x86 (310p)
- openEuler x86 (910b, ACL Graph)
- openEuler aarch64 (310p)
- openEuler aarch64 (910b, ACL Graph)

models : move the token embedding norms to the first layer (#20943)
- models : move the token embedding norms to the first layer
- cont : fix LLM_TENSOR_CONV1D + fix il indexing
macOS/iOS:
- macOS Apple Silicon (arm64)
- macOS Intel (x64)
- iOS XCFramework
Linux:
- Ubuntu x64 (CPU)
- Ubuntu x64 (Vulkan)
- Ubuntu x64 (ROCm 7.2)
- Ubuntu s390x (CPU)
- Ubuntu x64 (OpenVINO)
Windows:
- Windows x64 (CPU)
- Windows arm64 (CPU)
- Windows x64 (CUDA 12) - CUDA 12.4 DLLs
- Windows x64 (CUDA 13) - CUDA 13.1 DLLs
- Windows x64 (Vulkan)
- Windows x64 (SYCL)
- Windows x64 (HIP)
openEuler:
- openEuler x86 (310p)
- openEuler x86 (910b, ACL Graph)
- openEuler aarch64 (310p)
- openEuler aarch64 (910b, ACL Graph)

common : replace wrap_for_generation with a prefix convenience function and fix gpt-oss (#20912)
macOS/iOS:
- macOS Apple Silicon (arm64)
- macOS Intel (x64)
- iOS XCFramework
Linux:
- Ubuntu x64 (CPU)
- Ubuntu x64 (Vulkan)
- Ubuntu x64 (ROCm 7.2)
- Ubuntu s390x (CPU)
- Ubuntu x64 (OpenVINO)
Windows:
- Windows x64 (CPU)
- Windows arm64 (CPU)
- Windows x64 (CUDA 12) - CUDA 12.4 DLLs
- Windows x64 (CUDA 13) - CUDA 13.1 DLLs
- Windows x64 (Vulkan)
- Windows x64 (SYCL)
- Windows x64 (HIP)
openEuler:
- openEuler x86 (310p)
- openEuler x86 (910b, ACL Graph)
- openEuler aarch64 (310p)
- openEuler aarch64 (910b, ACL Graph)

mtmd: Add dynamic high-resolution image preprocessing for InternVL model (#20847)
- added support for internvl's dynamic high-resolution (Qianfan-OCR needed)
- add min/max dynamic patch to gguf meta
- clean up
- simplified handling min/max dynamic patch
- reuse llava_uhd logic for slice images
- provide default values for older models
- flake8
- prevent writing 0 value to gguf
- remove duplicated resolution candidates with a better algorithm
- fix indentation
- format
- add protection from divide by zero
- change to 0 to be safe
Co-authored-by: Xuan Son Nguyen son@huggingface.co
macOS/iOS:
- macOS Apple Silicon (arm64)
- macOS Intel (x64)
- iOS XCFramework
Linux:
- Ubuntu x64 (CPU)
- Ubuntu x64 (Vulkan)
- Ubuntu x64 (ROCm 7.2)
- Ubuntu s390x (CPU)
- Ubuntu x64 (OpenVINO)
Windows:
- Windows x64 (CPU)
- Windows arm64 (CPU)
- Windows x64 (CUDA 12) - CUDA 12.4 DLLs
- Windows x64 (CUDA 13) - CUDA 13.1 DLLs
- Windows x64 (Vulkan)
- Windows x64 (SYCL)
- Windows x64 (HIP)
openEuler:
- openEuler x86 (310p)
- openEuler x86 (910b, ACL Graph)
- openEuler aarch64 (310p)
- openEuler aarch64 (910b, ACL Graph)

misc : prefer ggml-org models in docs and examples (#20827)
- misc : prefer ggml-org models in docs and examples
Prefer referring to known-good quantizations under ggml-org rather than
3rd-party uploaders.
- remove accidentally committed file
macOS/iOS:
- macOS Apple Silicon (arm64)
- macOS Intel (x64)
- iOS XCFramework
Linux:
- Ubuntu x64 (CPU)
- Ubuntu x64 (Vulkan)
- Ubuntu x64 (ROCm 7.2)
- Ubuntu s390x (CPU)
- Ubuntu x64 (OpenVINO)
Windows:
- Windows x64 (CPU)
- Windows arm64 (CPU)
- Windows x64 (CUDA 12) - CUDA 12.4 DLLs
- Windows x64 (CUDA 13) - CUDA 13.1 DLLs
- Windows x64 (Vulkan)
- Windows x64 (SYCL)
- Windows x64 (HIP)
openEuler:
- openEuler x86 (310p)
- openEuler x86 (910b, ACL Graph)
- openEuler aarch64 (310p)
- openEuler aarch64 (910b, ACL Graph)

Add shader count for Intel Arc Pro B60 (#20818)
macOS/iOS:
- macOS Apple Silicon (arm64)
- macOS Intel (x64)
- iOS XCFramework
Linux:
- Ubuntu x64 (CPU)
- Ubuntu x64 (Vulkan)
- Ubuntu x64 (ROCm 7.2)
- Ubuntu s390x (CPU)
- Ubuntu x64 (OpenVINO)
Windows:
- Windows x64 (CPU)
- Windows arm64 (CPU)
- Windows x64 (CUDA 12) - CUDA 12.4 DLLs
- Windows x64 (CUDA 13) - CUDA 13.1 DLLs
- Windows x64 (Vulkan)
- Windows x64 (SYCL)
- Windows x64 (HIP)
openEuler:
- openEuler x86 (310p)
- openEuler x86 (910b, ACL Graph)
- openEuler aarch64 (310p)
- openEuler aarch64 (910b, ACL Graph)

mtmd: add clip_graph::build_mm() (#20751)
- clip: add build_mm()
- apply to all models
- add TODO for bias overload
macOS/iOS:
- macOS Apple Silicon (arm64)
- macOS Intel (x64)
- iOS XCFramework
Linux:
- Ubuntu x64 (CPU)
- Ubuntu x64 (Vulkan)
- Ubuntu x64 (ROCm 7.2)
- Ubuntu s390x (CPU)
- Ubuntu x64 (OpenVINO)
Windows:
- Windows x64 (CPU)
- Windows arm64 (CPU)
- Windows x64 (CUDA 12) - CUDA 12.4 DLLs
- Windows x64 (CUDA 13) - CUDA 13.1 DLLs
- Windows x64 (Vulkan)
- Windows x64 (SYCL)
- Windows x64 (HIP)
openEuler:
- openEuler x86 (310p)
- openEuler x86 (910b, ACL Graph)
- openEuler aarch64 (310p)
- openEuler aarch64 (910b, ACL Graph)

CANN: support flash attention for head dim not multiple of 16, fix ALiBi slope offset (#20031)
- Allow FLASH_ATTN_EXT when head dimension D is not a multiple of 16 by
padding Q/K/V to D_padded = GGML_PAD(D, 16), running FusedInferAttentionScoreV2,
then slicing the output back to D (ggml-cann.cpp + aclnn_ops.cpp).
- Fix aclnn_get_slope second-part offset: use ggml_type_size(dtype) instead of
sizeof(float) so ALiBi slopes are correct when dtype is F16 (e.g. GQA with
48 heads); fixes buffer overflow and large numerical errors in those cases.
macOS/iOS:
- macOS Apple Silicon (arm64)
- macOS Intel (x64)
- iOS XCFramework
Linux:
- Ubuntu x64 (CPU)
- Ubuntu x64 (Vulkan)
- Ubuntu x64 (ROCm 7.2)
- Ubuntu s390x (CPU)
- Ubuntu x64 (OpenVINO)
Windows:
- Windows x64 (CPU)
- Windows arm64 (CPU)
- Windows x64 (CUDA 12) - CUDA 12.4 DLLs
- Windows x64 (CUDA 13) - CUDA 13.1 DLLs
- Windows x64 (Vulkan)
- Windows x64 (SYCL)
- Windows x64 (HIP)
openEuler:
- openEuler x86 (310p)
- openEuler x86 (910b, ACL Graph)
- openEuler aarch64 (310p)
- openEuler aarch64 (910b, ACL Graph)

hexagon: add neg, exp, sigmoid, softplus ops, cont, repeat ops (#20701)
Add element-wise unary ops needed by Qwen 3.5's DeltaNet linear
attention layers. These ops follow the existing unary-ops pattern
with VTCM DMA double-buffering.
- neg: negate via scale by -1.0
- exp: uses existing hvx_exp_f32 HVX intrinsics
- sigmoid: uses existing hvx_sigmoid_f32_aa HVX intrinsics
- softplus: log(1 + exp(x)) scalar fallback
- CONT reuses the existing CPY infrastructure since making a tensor
contiguous is equivalent to a same-type copy.
- REPEAT implements tiled memory copy with multi-threaded execution via
the worker pool, supporting f32 and f16 types. The kernel parallelizes
across output rows and uses memcpy for each tile.
Co-authored-by: Max Krasnyansky maxk@qti.qualcomm.com
macOS/iOS:
- macOS Apple Silicon (arm64)
- macOS Intel (x64)
- iOS XCFramework
Linux:
- Ubuntu x64 (CPU)
- Ubuntu x64 (Vulkan)
- Ubuntu x64 (ROCm 7.2)
- Ubuntu s390x (CPU)
- Ubuntu x64 (OpenVINO)
Windows:
- Windows x64 (CPU)
- Windows arm64 (CPU)
- Windows x64 (CUDA 12) - CUDA 12.4 DLLs
- Windows x64 (CUDA 13) - CUDA 13.1 DLLs
- Windows x64 (Vulkan)
- Windows x64 (SYCL)
- Windows x64 (HIP)
openEuler:
- openEuler x86 (310p)
- openEuler x86 (910b, ACL Graph)
- openEuler aarch64 (310p)
- openEuler aarch64 (910b, ACL Graph)

[SYCL] ehance UPSCALE to support all UT cases (#20637)
- [SYCL] ehance UPSCALE to support more cases
- rm test case result of SYCL1
macOS/iOS:
- macOS Apple Silicon (arm64)
- macOS Intel (x64)
- iOS XCFramework
Linux:
- Ubuntu x64 (CPU)
- Ubuntu x64 (Vulkan)
- Ubuntu x64 (ROCm 7.2)
- Ubuntu s390x (CPU)
- Ubuntu x64 (OpenVINO)
Windows:
- Windows x64 (CPU)
- Windows arm64 (CPU)
- Windows x64 (CUDA 12) - CUDA 12.4 DLLs
- Windows x64 (CUDA 13) - CUDA 13.1 DLLs
- Windows x64 (Vulkan)
- Windows x64 (SYCL)
- Windows x64 (HIP)
openEuler:
- openEuler x86 (310p)
- openEuler x86 (910b, ACL Graph)
- openEuler aarch64 (310p)
- openEuler aarch64 (910b, ACL Graph)

CUDA: GDN hide memory latency (#20537)
macOS/iOS:
- macOS Apple Silicon (arm64)
- macOS Intel (x64)
- iOS XCFramework
Linux:
- Ubuntu x64 (CPU)
- Ubuntu x64 (Vulkan)
- Ubuntu x64 (ROCm 7.2)
- Ubuntu s390x (CPU)
- Ubuntu x64 (OpenVINO)
Windows:
- Windows x64 (CPU)
- Windows arm64 (CPU)
- Windows x64 (CUDA 12) - CUDA 12.4 DLLs
- Windows x64 (CUDA 13) - CUDA 13.1 DLLs
- Windows x64 (Vulkan)
- Windows x64 (SYCL)
- Windows x64 (HIP)
openEuler:
- openEuler x86 (310p)
- openEuler x86 (910b, ACL Graph)
- openEuler aarch64 (310p)
- openEuler aarch64 (910b, ACL Graph)

model : wire up Qwen3.5/Qwen3.5MoE tensors for NVFP4 support (#20506)
macOS/iOS:
- macOS Apple Silicon (arm64)
- macOS Intel (x64)
- iOS XCFramework
Linux:
- Ubuntu x64 (CPU)
- Ubuntu x64 (Vulkan)
- Ubuntu x64 (ROCm 7.2)
- Ubuntu s390x (CPU)
- Ubuntu x64 (OpenVINO)
Windows:
- Windows x64 (CPU)
- Windows arm64 (CPU)
- Windows x64 (CUDA 12) - CUDA 12.4 DLLs
- Windows x64 (CUDA 13) - CUDA 13.1 DLLs
- Windows x64 (Vulkan)
- Windows x64 (SYCL)
- Windows x64 (HIP)
openEuler:
- openEuler x86 (310p)
- openEuler x86 (910b, ACL Graph)
- openEuler aarch64 (310p)
- openEuler aarch64 (910b, ACL Graph)

tools : enable kvu in perplexity for hellaswag, winogrande, multiple-choice (#19954)
llama-perplexity -hf unsloth/Qwen3-0.6B-GGUF:Q4_K_M -f winogrande-debiased-eval.csv --winogrande
winogrande_score : tokenizing selected tasks
winogrande_score : calculating winogrande score over selected tasks.
split_equal: sequential split is not supported when there are coupled sequences in the input batch (you may need to use the -kvu flag)
decode: failed to find a memory slot for batch of size 46
failed to decode the batch, n_batch = 2048, ret = 1
winogrande_score: llama_decode() failed
same for hellaswag:
split_equal: sequential split is not supported when there are coupled sequences in the input batch (you may need to use the -kvu flag)
decode: failed to find a memory slot for batch of size 99
failed to decode the batch, n_batch = 2048, ret = 1
hellaswag_score: llama_decode() failed
Signed-off-by: Adrien Gallouët angt@huggingface.co
macOS/iOS:
- macOS Apple Silicon (arm64)
- macOS Intel (x64)
- iOS XCFramework
Linux:
- Ubuntu x64 (CPU)
- Ubuntu x64 (Vulkan)
- Ubuntu x64 (ROCm 7.2)
- Ubuntu s390x (CPU)
Windows:
- Windows x64 (CPU)
- Windows arm64 (CPU)
- Windows x64 (CUDA 12) - CUDA 12.4 DLLs
- Windows x64 (CUDA 13) - CUDA 13.1 DLLs
- Windows x64 (Vulkan)
- Windows x64 (SYCL)
- Windows x64 (HIP)
openEuler:
- openEuler x86 (310p)
- openEuler x86 (910b, ACL Graph)
- openEuler aarch64 (310p)
- openEuler aarch64 (910b, ACL Graph)

vulkan: add GATED_DELTA_NET op support (#20334)
- vulkan: add GATED_DELTA_NET op support
Implements the fused gated delta net recurrence as a Vulkan compute
shader with full support for scalar gate, KDA vector gate, GQA
broadcast, multi-token sequences, and permuted (non-contiguous) q/k
inputs. Specialization constants select head size (32/64/128) and
KDA mode at pipeline creation time.
Passes all 13 test-backend-ops cases on AMD Radeon 890M (RADV GFX1150).
Co-Authored-By: Claude Opus 4.6 noreply@anthropic.com
- vulkan: optimize GATED_DELTA_NET shader (Phase 1)
- vec4 dot products on all inner loops (dp4 hardware intrinsic)
- Cache exp(g) in shared memory for KDA path, eliminating ~32K
redundant global reads and ~16K redundant exp() calls per token
- vec4 fused decay + rank-1 update (3 vec4 ops vs 12 scalar ops)
- Add perf benchmark cases for GATED_DELTA_NET to test-backend-ops
KDA TG: +5.4% throughput. Non-KDA: no regressions.
13/13 test-backend-ops passing on AMD Radeon 890M (RADV GFX1150).
Co-Authored-By: Claude Opus 4.6 noreply@anthropic.com
- vulkan: address review feedback for GATED_DELTA_NET
Pipeline array refactor [3][2], A_TYPE/D_TYPE/FLOAT_TYPE shader macros,
scale in push constants, supports_op fix, dispatch restructuring.
Co-Authored-By: Claude Opus 4.6 noreply@anthropic.com
- vulkan: use FLOAT_TYPE for buffer/shared declarations, align formatting
Co-Authored-By: Claude Opus 4.6 noreply@anthropic.com
- vulkan: add explicit FLOAT_TYPE casts for buffer loads
Wrap data_q, data_k, and data_g buffer reads with FLOAT_TYPE() casts
to ensure correct behavior across all Vulkan configurations.
Co-Authored-By: Claude Opus 4.6 noreply@anthropic.com
- vulkan: fix Q/K broadcast for interleaved head layout
Adapt to the interleaved broadcast convention from #20340:
head_id / rq1 → head_id % neq1
Co-Authored-By: Claude Opus 4.6 noreply@anthropic.com
Co-authored-by: Progeny Alpha ProgenyAlpha@users.noreply.github.com
Co-authored-by: Claude Opus 4.6 noreply@anthropic.com
macOS/iOS:
- macOS Apple Silicon (arm64)
- macOS Intel (x64)
- iOS XCFramework
Linux:
- Ubuntu x64 (CPU)
- Ubuntu x64 (Vulkan)
- Ubuntu x64 (ROCm 7.2)
- Ubuntu s390x (CPU)
Windows:
- Windows x64 (CPU)
- Windows arm64 (CPU)
- Windows x64 (CUDA 12) - CUDA 12.4 DLLs
- Windows x64 (CUDA 13) - CUDA 13.1 DLLs
- Windows x64 (Vulkan)
- Windows x64 (SYCL)
- Windows x64 (HIP)
openEuler:
- openEuler x86 (310p)
- openEuler x86 (910b, ACL Graph)
- openEuler aarch64 (310p)
- openEuler aarch64 (910b, ACL Graph)

metal : fix q5_k mul_mv register spill (#20399)
macOS/iOS:
- macOS Apple Silicon (arm64)
- macOS Intel (x64)
- iOS XCFramework
Linux:
- Ubuntu x64 (CPU)
- Ubuntu x64 (Vulkan)
- Ubuntu x64 (ROCm 7.2)
- Ubuntu s390x (CPU)
Windows:
- Windows x64 (CPU)
- Windows arm64 (CPU)
- Windows x64 (CUDA 12) - CUDA 12.4 DLLs
- Windows x64 (CUDA 13) - CUDA 13.1 DLLs
- Windows x64 (Vulkan)
- Windows x64 (SYCL)
- Windows x64 (HIP)
openEuler:
- openEuler x86 (310p)
- openEuler x86 (910b, ACL Graph)
- openEuler aarch64 (310p)
- openEuler aarch64 (910b, ACL Graph)

models : fix assert in mamba2 (cont) (#20335)
- models : fix assert in mamba2 (cont)
- cont : add n_group mod
Co-authored-by: Sigbjørn Skjæret sigbjorn.skjaeret@scala.com
Co-authored-by: Sigbjørn Skjæret sigbjorn.skjaeret@scala.com
macOS/iOS:
- macOS Apple Silicon (arm64)
- macOS Intel (x64)
- iOS XCFramework
Linux:
- Ubuntu x64 (CPU)
- Ubuntu x64 (Vulkan)
- Ubuntu x64 (ROCm 7.2)
- Ubuntu s390x (CPU)
Windows:
- Windows x64 (CPU)
- Windows arm64 (CPU)
- Windows x64 (CUDA 12) - CUDA 12.4 DLLs
- Windows x64 (CUDA 13) - CUDA 13.1 DLLs
- Windows x64 (Vulkan)
- Windows x64 (SYCL)
- Windows x64 (HIP)
openEuler:
- openEuler x86 (310p)
- openEuler x86 (910b, ACL Graph)
- openEuler aarch64 (310p)
- openEuler aarch64 (910b, ACL Graph)

metal : extend mul_mv_ext to BF16, Q2_K, Q3_K (#20250)
Enable mul_mv_ext small-batch kernels (BS 2-8) for BF16, Q2_K,
and Q3_K quantization types. These types previously fell through
to the slower single-row mul_mv path.
BF16 uses the float4 dequantize path (like F16). Q2_K and Q3_K
use the float4x4 K-quant path (like Q4_K/Q5_K/Q6_K).
Co-authored-by: Claude Opus 4.6 noreply@anthropic.com
macOS/iOS:
- macOS Apple Silicon (arm64)
- macOS Intel (x64)
- iOS XCFramework
Linux:
- Ubuntu x64 (CPU)
- Ubuntu x64 (Vulkan)
- Ubuntu x64 (ROCm 7.2)
- Ubuntu s390x (CPU)
Windows:
- Windows x64 (CPU)
- Windows arm64 (CPU)
- Windows x64 (CUDA 12) - CUDA 12.4 DLLs
- Windows x64 (CUDA 13) - CUDA 13.1 DLLs
- Windows x64 (Vulkan)
- Windows x64 (SYCL)
- Windows x64 (HIP)
openEuler:
- openEuler x86 (310p)
- openEuler x86 (910b, ACL Graph)
- openEuler aarch64 (310p)
- openEuler aarch64 (910b, ACL Graph)

llama-bench: introduce -hf and -hff flags & use --mmap 1 by default (#20211)
macOS/iOS:
- macOS Apple Silicon (arm64)
- macOS Intel (x64)
- iOS XCFramework
Linux:
- Ubuntu x64 (CPU)
- Ubuntu x64 (Vulkan)
- Ubuntu x64 (ROCm 7.2)
- Ubuntu s390x (CPU)
Windows:
- Windows x64 (CPU)
- Windows arm64 (CPU)
- Windows x64 (CUDA 12) - CUDA 12.4 DLLs
- Windows x64 (CUDA 13) - CUDA 13.1 DLLs
- Windows x64 (Vulkan)
- Windows x64 (SYCL)
- Windows x64 (HIP)
openEuler:
- openEuler x86 (310p)
- openEuler x86 (910b, ACL Graph)
- openEuler aarch64 (310p)
- openEuler aarch64 (910b, ACL Graph)

ggml: add GATED_DELTA_NET op (#19504)
- ggml: add GATED_DELTA_NET op
- remove the transpose
- add KDA
- add qwen35 dense
- llama : check for fused gated delta net backend support
Co-authored-by: Georgi Gerganov ggerganov@gmail.com
macOS/iOS:
- macOS Apple Silicon (arm64)
- macOS Intel (x64)
- iOS XCFramework
Linux:
- Ubuntu x64 (CPU)
- Ubuntu x64 (Vulkan)
- Ubuntu x64 (ROCm 7.2)
- Ubuntu s390x (CPU)
Windows:
- Windows x64 (CPU)
- Windows arm64 (CPU)
- Windows x64 (CUDA 12) - CUDA 12.4 DLLs
- Windows x64 (CUDA 13) - CUDA 13.1 DLLs
- Windows x64 (Vulkan)
- Windows x64 (SYCL)
- Windows x64 (HIP)
openEuler:
- openEuler x86 (310p)
- openEuler x86 (910b, ACL Graph)
- openEuler aarch64 (310p)
- openEuler aarch64 (910b, ACL Graph)

Autoparser - complete refactoring of parser architecture (#18675)
- Autoparser - full single commit squish
- Final pre-merge changes: minor fixes, Kimi 2.5 model parser
macOS/iOS:
- macOS Apple Silicon (arm64)
- macOS Intel (x64)
- iOS XCFramework
Linux:
- Ubuntu x64 (CPU)
- Ubuntu x64 (Vulkan)
- Ubuntu x64 (ROCm 7.2)
- Ubuntu s390x (CPU)
Windows:
- Windows x64 (CPU)
- Windows arm64 (CPU)
- Windows x64 (CUDA 12) - CUDA 12.4 DLLs
- Windows x64 (CUDA 13) - CUDA 13.1 DLLs
- Windows x64 (Vulkan)
- Windows x64 (SYCL)
- Windows x64 (HIP)
openEuler:
- openEuler x86 (310p)
- openEuler x86 (910b, ACL Graph)
- openEuler aarch64 (310p)
- openEuler aarch64 (910b, ACL Graph)

hexagon: add fp16 support for binary ops: add,sub,mul,div (#20139)
- hexagon: add fp16 support for binary ops: add,sub,mul,div
- hexagon: fix test-backend-ops failures for fp16 binary ops on older arches (<v79)
- hexagon: decide on n_threads (aka n_jobs) early to avoid overallocating scratchpad
- snapdragon: fix readme link
Co-authored-by: Max Krasnyansky maxk@qti.qualcomm.com
macOS/iOS:
- macOS Apple Silicon (arm64)
- macOS Intel (x64)
- iOS XCFramework
Linux:
- Ubuntu x64 (CPU)
- Ubuntu x64 (Vulkan)
- Ubuntu x64 (ROCm 7.2)
- Ubuntu s390x (CPU)
Windows:
- Windows x64 (CPU)
- Windows arm64 (CPU)
- Windows x64 (CUDA 12) - CUDA 12.4 DLLs
- Windows x64 (CUDA 13) - CUDA 13.1 DLLs
- Windows x64 (Vulkan)
- Windows x64 (SYCL)
- Windows x64 (HIP)
openEuler:
- openEuler x86 (310p)
- openEuler x86 (910b, ACL Graph)
- openEuler aarch64 (310p)
- openEuler aarch64 (910b, ACL Graph)

[WebGPU] Fix wait logic for inflight jobs (#20096)
- Enable tmate debugging for investigating thread safety issue
- Refactor wait and submit to operate on vectorwgpu::FutureWaitInfo, and fix wait to delete only the future that is completed.
- Cleanup
- Remove clear change and run clang-format
- Cleanup
macOS/iOS:
- macOS Apple Silicon (arm64)
- macOS Intel (x64)
- iOS XCFramework
Linux:
- Ubuntu x64 (CPU)
- Ubuntu x64 (Vulkan)
- Ubuntu x64 (ROCm 7.2)
- Ubuntu s390x (CPU)
Windows:
- Windows x64 (CPU)
- Windows arm64 (CPU)
- Windows x64 (CUDA 12) - CUDA 12.4 DLLs
- Windows x64 (CUDA 13) - CUDA 13.1 DLLs
- Windows x64 (Vulkan)
- Windows x64 (SYCL)
- Windows x64 (HIP)
openEuler:
- openEuler x86 (310p)
- openEuler x86 (910b, ACL Graph)
- openEuler aarch64 (310p)
- openEuler aarch64 (910b, ACL Graph)

kleidiai : add sme fp16 compute path for q4_0 gemm on aarch64 (#20043)
macOS/iOS:
- macOS Apple Silicon (arm64)
- macOS Intel (x64)
- iOS XCFramework
Linux:
- Ubuntu x64 (CPU)
- Ubuntu x64 (Vulkan)
- Ubuntu x64 (ROCm 7.2)
- Ubuntu s390x (CPU)
Windows:
- Windows x64 (CPU)
- Windows arm64 (CPU)
- Windows x64 (CUDA 12) - CUDA 12.4 DLLs
- Windows x64 (CUDA 13) - CUDA 13.1 DLLs
- Windows x64 (Vulkan)
- Windows x64 (SYCL)
- Windows x64 (HIP)
openEuler:
- openEuler x86 (310p)
- openEuler x86 (910b, ACL Graph)
- openEuler aarch64 (310p)
- openEuler aarch64 (910b, ACL Graph)

opencl: add optimized q4_1 mm kernel for adreno (#19840)
- Add Q4_1 OpenCL Kernels
- opencl: refactor transpose
- opencl: format
- opencl: refactor q4_1 unpack
- opencl: move ggml_cl_mul_mat_q4_1_f32_adreno
- opencl: refactor ggml_cl_mul_mat_q4_1_f32_adreno and kernels
- opencl: rename kernel files and kernes
- opencl: fix build for non adreno
- opencl: move code around and format
Co-authored-by: Li He lih@qti.qualcomm.com
macOS/iOS:
- macOS Apple Silicon (arm64)
- macOS Intel (x64)
- iOS XCFramework
Linux:
- Ubuntu x64 (CPU)
- Ubuntu x64 (Vulkan)
- Ubuntu x64 (ROCm 7.2)
- Ubuntu s390x (CPU)
Windows:
- Windows x64 (CPU)
- Windows arm64 (CPU)
- Windows x64 (CUDA 12) - CUDA 12.4 DLLs
- Windows x64 (CUDA 13) - CUDA 13.1 DLLs
- Windows x64 (Vulkan)
- Windows x64 (SYCL)
- Windows x64 (HIP)
openEuler:
- openEuler x86 (310p)
- openEuler x86 (910b, ACL Graph)
- openEuler aarch64 (310p)
- openEuler aarch64 (910b, ACL Graph)

vulkan: improve partial offloading performance on AMD (#19976)
- vulkan: fix and enable cpy_tensor_async function
- use transfer_queue for async transfers on AMD, synchronize with timeline semaphore
- update offload_op logic
- fix missing transfer submission
- disable async transfer queue on AMD GCN
- revert op batch size change
- fix cpy_tensor_async checks
macOS/iOS:
- macOS Apple Silicon (arm64)
- macOS Intel (x64)
- iOS XCFramework
Linux:
- Ubuntu x64 (CPU)
- Ubuntu x64 (Vulkan)
- Ubuntu x64 (ROCm 7.2)
- Ubuntu s390x (CPU)
Windows:
- Windows x64 (CPU)
- Windows arm64 (CPU)
- Windows x64 (CUDA 12) - CUDA 12.4 DLLs
- Windows x64 (CUDA 13) - CUDA 13.1 DLLs
- Windows x64 (Vulkan)
- Windows x64 (SYCL)
- Windows x64 (HIP)
openEuler:
- openEuler x86 (310p)
- openEuler x86 (910b, ACL Graph)
- openEuler aarch64 (310p)
- openEuler aarch64 (910b, ACL Graph)

vendors : update miniaudio library to 0.11.24 (#19914)
macOS/iOS:
- macOS Apple Silicon (arm64)
- macOS Intel (x64)
- iOS XCFramework
Linux:
- Ubuntu x64 (CPU)
- Ubuntu x64 (Vulkan)
- Ubuntu x64 (ROCm 7.2)
- Ubuntu s390x (CPU)
Windows:
- Windows x64 (CPU)
- Windows arm64 (CPU)
- Windows x64 (CUDA 12) - CUDA 12.4 DLLs
- Windows x64 (CUDA 13) - CUDA 13.1 DLLs
- Windows x64 (Vulkan)
- Windows x64 (SYCL)
- Windows x64 (HIP)
openEuler:
- openEuler x86 (310p)
- openEuler x86 (910b, ACL Graph)
- openEuler aarch64 (310p)
- openEuler aarch64 (910b, ACL Graph)

CUDA: add CDNA3 MFMA support for flash attention MMA kernel (#19806)
- CUDA: add CDNA3 MFMA support for flash attention MMA kernel
Add MI300X (gfx942) MFMA tensor core flash attention using
v_mfma_f32_16x16x16_f16 (FP16 in, FP32 accumulate).
- Add FATTN_WARP_SIZE=64 for CDNA wavefront64
- Add CDNA config for head sizes 64, 80, 96, 112, 128
- Add FP16 MFMA intrinsic path in mma.cuh
- Add manual V transpose load for MFMA register layout
- Route CDNA to MMA for prompt processing, VEC for token generation
- Fix Q loading and combine stride granularity for non-power-of-2 heads
Benchmarks (Qwen2.5-1.5B Q4_K_M, MI300X):
pp512 +7%, pp1024 +13%, pp2048 +23%, pp4096 +39%
tg128 -10% (FA overhead, VEC used for both)
All 2480 flash attention tests pass.
Ref: #17917
- address review: replace FATTN_WARP_SIZE with constexpr, improve dispatch
- Replace #define FATTN_WARP_SIZE with constexpr int warp_size =
ggml_cuda_get_physical_warp_size() in each device function
- Use ne[1]*gqa_ratio threshold for MMA vs tile dispatch. Benchmarked
crossover on MI300X @ d32768 with power-of-2 GQA models:
hsk=64 (Llama 1B, gqa=4): MMA wins at eff >= 128 (+11%)
hsk=128 (Llama 3B, gqa=4): MMA wins at eff >= 128 (+4%)
Unified threshold: eff_nq >= 128 for all head sizes.
- Remove VEC fallback; small batches fall through to tile kernel
- Update ggml/src/ggml-cuda/fattn.cu
- use ggml_cuda_info().devices warp_size instead of hardcoded check
Co-authored-by: Johannes Gäßler johannesg@5d6.de
macOS/iOS:
- macOS Apple Silicon (arm64)
- macOS Intel (x64)
- iOS XCFramework
Linux:
- Ubuntu x64 (CPU)
- Ubuntu x64 (Vulkan)
- Ubuntu x64 (ROCm 7.2)
- Ubuntu s390x (CPU)
Windows:
- Windows x64 (CPU)
- Windows arm64 (CPU)
- Windows x64 (CUDA 12) - CUDA 12.4 DLLs
- Windows x64 (CUDA 13) - CUDA 13.1 DLLs
- Windows x64 (Vulkan)
- Windows x64 (SYCL)
- Windows x64 (HIP)
openEuler:
- openEuler x86 (310p)
- openEuler x86 (910b, ACL Graph)
- openEuler aarch64 (310p)
- openEuler aarch64 (910b, ACL Graph)

replace the magic nunber 768 by max work group size to support iGPU (#19920)
Co-authored-by: Neo Zhang Jianyu jianyu.zhang@intel.com
macOS/iOS:
- macOS Apple Silicon (arm64)
- macOS Intel (x64)
- iOS XCFramework
Linux:
- Ubuntu x64 (CPU)
- Ubuntu x64 (Vulkan)
- Ubuntu x64 (ROCm 7.2)
- Ubuntu s390x (CPU)
Windows:
- Windows x64 (CPU)
- Windows arm64 (CPU)
- Windows x64 (CUDA 12) - CUDA 12.4 DLLs
- Windows x64 (CUDA 13) - CUDA 13.1 DLLs
- Windows x64 (Vulkan)
- Windows x64 (SYCL)
- Windows x64 (HIP)
openEuler:
- openEuler x86 (310p)
- openEuler x86 (910b, ACL Graph)
- openEuler aarch64 (310p)
- openEuler aarch64 (910b, ACL Graph)

models : fix graph splits (#19866)
macOS/iOS:
- macOS Apple Silicon (arm64)
- macOS Intel (x64)
- iOS XCFramework
Linux:
- Ubuntu x64 (CPU)
- Ubuntu x64 (Vulkan)
- Ubuntu x64 (ROCm 7.2)
- Ubuntu s390x (CPU)
Windows:
- Windows x64 (CPU)
- Windows arm64 (CPU)
- Windows x64 (CUDA 12) - CUDA 12.4 DLLs
- Windows x64 (CUDA 13) - CUDA 13.1 DLLs
- Windows x64 (Vulkan)
- Windows x64 (SYCL)
- Windows x64 (HIP)
openEuler:
- openEuler x86 (310p)
- openEuler x86 (910b, ACL Graph)
- openEuler aarch64 (310p)
- openEuler aarch64 (910b, ACL Graph)

hexagon refactor all Ops to use local context struct (#19819)
- hexagon: refactor set/get/sum-rows ops to use local context
- hexagon: refactor ROPE and Softmax Ops to use local context
Improves performance a bit by precomputing things and saving in the context.
- hexagon: refactor activation ops to use local context struct
- hexagon: refactor unary ops to use local context struct and DMA/VTCM
- hexagon: use aligned hvx_scale function
- hexagon: remove unused fields from op_context
- hexagon: rewrite ROPE to use DMA and VTCM scratchpad
- hex-rope: keep N rows in scratchpad (instead of just two)
- hex-rope: introduce rowidx cache
- hex-rope: remove unused fields
- hex-rope: rewrite dma prefetch logic to allow for multi-row fetch/compute
also removes the need for fastdiv.
- hex-rope: minor formatting
- hex-rope: use indices and unroll the loops
- hex-rope: more updates to cleanup rope-block handling
- hexagon: cleanup supported type/dims checks
- hexagon: all reduce funcs replicated across lanes
There is no need to explicitly replicate the first value.
- snapdragon: update adb and windows scripts to use ubatch-size 256
Updated Ops support handles larger ubatches.
macOS/iOS:
- macOS Apple Silicon (arm64)
- macOS Intel (x64)
- iOS XCFramework
Linux:
- Ubuntu x64 (CPU)
- Ubuntu x64 (Vulkan)
- Ubuntu x64 (ROCm 7.2)
- Ubuntu s390x (CPU)
Windows:
- Windows x64 (CPU)
- Windows arm64 (CPU)
- Windows x64 (CUDA 12) - CUDA 12.4 DLLs
- Windows x64 (CUDA 13) - CUDA 13.1 DLLs
- Windows x64 (Vulkan)
- Windows x64 (SYCL)
- Windows x64 (HIP)
openEuler:
- openEuler x86 (310p)
- openEuler x86 (910b, ACL Graph)
- openEuler aarch64 (310p)
- openEuler aarch64 (910b, ACL Graph)

cli : provide model with text filename (#19783)
macOS/iOS:
- macOS Apple Silicon (arm64)
- macOS Intel (x64)
- iOS XCFramework
Linux:
- Ubuntu x64 (CPU)
- Ubuntu x64 (Vulkan)
- Ubuntu x64 (ROCm 7.2)
- Ubuntu s390x (CPU)
Windows:
- Windows x64 (CPU)
- Windows arm64 (CPU)
- Windows x64 (CUDA 12) - CUDA 12.4 DLLs
- Windows x64 (CUDA 13) - CUDA 13.1 DLLs
- Windows x64 (Vulkan)
- Windows x64 (SYCL)
- Windows x64 (HIP)
openEuler:
- openEuler x86 (310p)
- openEuler x86 (910b, ACL Graph)
- openEuler aarch64 (310p)
- openEuler aarch64 (910b, ACL Graph)

hexagon : fix build release (#19444) (#19587)
macOS/iOS:
- macOS Apple Silicon (arm64)
- macOS Intel (x64)
- iOS XCFramework
Linux:
- Ubuntu x64 (CPU)
- Ubuntu x64 (Vulkan)
- Ubuntu s390x (CPU)
Windows:
- Windows x64 (CPU)
- Windows arm64 (CPU)
- Windows x64 (CUDA 12) - CUDA 12.4 DLLs
- Windows x64 (CUDA 13) - CUDA 13.1 DLLs
- Windows x64 (Vulkan)
- Windows x64 (SYCL)
- Windows x64 (HIP)
openEuler:
- openEuler x86 (310p)
- openEuler x86 (910b, ACL Graph)
- openEuler aarch64 (310p)
- openEuler aarch64 (910b, ACL Graph)

test: mul_mat tests with huge batch size (#19519)
macOS/iOS:
- macOS Apple Silicon (arm64)
- macOS Intel (x64)
- iOS XCFramework
Linux:
- Ubuntu x64 (CPU)
- Ubuntu x64 (Vulkan)
- Ubuntu s390x (CPU)
Windows:
- Windows x64 (CPU)
- Windows arm64 (CPU)
- Windows x64 (CUDA 12) - CUDA 12.4 DLLs
- Windows x64 (CUDA 13) - CUDA 13.1 DLLs
- Windows x64 (Vulkan)
- Windows x64 (SYCL)
- Windows x64 (HIP)
openEuler:
- openEuler x86 (310p)
- openEuler x86 (910b, ACL Graph)
- openEuler aarch64 (310p)
- openEuler aarch64 (910b, ACL Graph)

ggml webgpu: Fix bug in dispatching large matrix-vector multiplication (#19535)
- Fix bug in dispatching large matrix-vector multiplication
macOS/iOS:
- macOS Apple Silicon (arm64)
- macOS Intel (x64)
- iOS XCFramework
Linux:
- Ubuntu x64 (CPU)
- Ubuntu x64 (Vulkan)
- Ubuntu s390x (CPU)
Windows:
- Windows x64 (CPU)
- Windows arm64 (CPU)
- Windows x64 (CUDA 12) - CUDA 12.4 DLLs
- Windows x64 (CUDA 13) - CUDA 13.1 DLLs
- Windows x64 (Vulkan)
- Windows x64 (SYCL)
- Windows x64 (HIP)
openEuler:
- openEuler x86 (310p)
- openEuler x86 (910b, ACL Graph)
- openEuler aarch64 (310p)
- openEuler aarch64 (910b, ACL Graph)

opencl: refactor expm1 and softplus (#19404)
- opencl: refactor expm1
- opencl: refactor softplus
- opencl: use h for half literals
Co-authored-by: Li He lih@qti.qualcomm.com
macOS/iOS:
- macOS Apple Silicon (arm64)
- macOS Intel (x64)
- iOS XCFramework
Linux:
- Ubuntu x64 (CPU)
- Ubuntu x64 (Vulkan)
- Ubuntu s390x (CPU)
Windows:
- Windows x64 (CPU)
- Windows arm64 (CPU)
- Windows x64 (CUDA 12) - CUDA 12.4 DLLs
- Windows x64 (CUDA 13) - CUDA 13.1 DLLs
- Windows x64 (Vulkan)
- Windows x64 (SYCL)
- Windows x64 (HIP)
openEuler:
- openEuler x86 (310p)
- openEuler x86 (910b, ACL Graph)
- openEuler aarch64 (310p)
- openEuler aarch64 (910b, ACL Graph)

convert : add JoyAI-LLM-Flash (#19651)
- convert_hf_to_gguf: add JoyAI-LLM-Flash tokenizer hash mapping to deepseek-v3
- llama-vocab: create a new pre-tokenizer name for joyai-llm.
- add missing vocab type section
- Update convert_hf_to_gguf_update.py
Co-authored-by: Sigbjørn Skjæret sigbjorn.skjaeret@scala.com
- Update convert_hf_to_gguf.py
Co-authored-by: Sigbjørn Skjæret sigbjorn.skjaeret@scala.com
Co-authored-by: Sigbjørn Skjæret sigbjorn.skjaeret@scala.com
macOS/iOS:
- macOS Apple Silicon (arm64)
- macOS Intel (x64)
- iOS XCFramework
Linux:
- Ubuntu x64 (CPU)
- Ubuntu x64 (Vulkan)
- Ubuntu s390x (CPU)
Windows:
- Windows x64 (CPU)
- Windows arm64 (CPU)
- Windows x64 (CUDA 12) - CUDA 12.4 DLLs
- Windows x64 (CUDA 13) - CUDA 13.1 DLLs
- Windows x64 (Vulkan)
- Windows x64 (SYCL)
- Windows x64 (HIP)
openEuler:
- openEuler x86 (310p)
- openEuler x86 (910b, ACL Graph)
- openEuler aarch64 (310p)
- openEuler aarch64 (910b, ACL Graph)

sync : ggml
macOS/iOS:
- macOS Apple Silicon (arm64)
- macOS Intel (x64)
- iOS XCFramework
Linux:
- Ubuntu x64 (CPU)
- Ubuntu x64 (Vulkan)
- Ubuntu s390x (CPU)
Windows:
- Windows x64 (CPU)
- Windows arm64 (CPU)
- Windows x64 (CUDA 12) - CUDA 12.4 DLLs
- Windows x64 (CUDA 13) - CUDA 13.1 DLLs
- Windows x64 (Vulkan)
- Windows x64 (SYCL)
- Windows x64 (HIP)
openEuler:
- openEuler x86 (310p)
- openEuler x86 (910b, ACL Graph)
- openEuler aarch64 (310p)
- openEuler aarch64 (910b, ACL Graph)

ggml-cpu: FA add GEMM microkernel (#19422)
- ggml-cpu: FA add GEMM microkernel
- add guard for sizeless vector types
- fix case where DV % GGML_F32_EPR !=0
- move memset out of the loop
- move another memset out of the loop
- use RM=4 for arm
- simd_gemm: convert everything to int
- convert everything to size_t to avoid warnings
- fixup
- add pragma for ignoring aggressive loop optimizations
macOS/iOS:
- macOS Apple Silicon (arm64)
- macOS Intel (x64)
- iOS XCFramework
Linux:
- Ubuntu x64 (CPU)
- Ubuntu x64 (Vulkan)
- Ubuntu s390x (CPU)
Windows:
- Windows x64 (CPU)
- Windows arm64 (CPU)
- Windows x64 (CUDA 12) - CUDA 12.4 DLLs
- Windows x64 (CUDA 13) - CUDA 13.1 DLLs
- Windows x64 (Vulkan)
- Windows x64 (SYCL)
- Windows x64 (HIP)
openEuler:
- openEuler x86 (310p)
- openEuler x86 (910b, ACL Graph)
- openEuler aarch64 (310p)
- openEuler aarch64 (910b, ACL Graph)

vulkan: restore -inf check in FA shaders (#19582)
macOS/iOS:
- macOS Apple Silicon (arm64)
- macOS Intel (x64)
- iOS XCFramework
Linux:
- Ubuntu x64 (CPU)
- Ubuntu x64 (Vulkan)
- Ubuntu s390x (CPU)
Windows:
- Windows x64 (CPU)
- Windows arm64 (CPU)
- Windows x64 (CUDA 12) - CUDA 12.4 DLLs
- Windows x64 (CUDA 13) - CUDA 13.1 DLLs
- Windows x64 (Vulkan)
- Windows x64 (SYCL)
- Windows x64 (HIP)
openEuler:
- openEuler x86 (310p)
- openEuler x86 (910b, ACL Graph)
- openEuler aarch64 (310p)
- openEuler aarch64 (910b, ACL Graph)

opencl: add basic support for q4_1 (#19534)
- opencl: add q4_1 mv
- opencl: clean up
- opencl: add flattened q4_1 mv
- opencl: clean up
- opencl: add basic q4_1 mm
- opencl: fix whitespace
- opencl: add general q4_0 mm
macOS/iOS:
- macOS Apple Silicon (arm64)
- macOS Intel (x64)
- iOS XCFramework
Linux:
- Ubuntu x64 (CPU)
- Ubuntu x64 (Vulkan)
- Ubuntu s390x (CPU)
Windows:
- Windows x64 (CPU)
- Windows arm64 (CPU)
- Windows x64 (CUDA 12) - CUDA 12.4 DLLs
- Windows x64 (CUDA 13) - CUDA 13.1 DLLs
- Windows x64 (Vulkan)
- Windows x64 (SYCL)
- Windows x64 (HIP)
openEuler:
- openEuler x86 (310p)
- openEuler x86 (910b, ACL Graph)
- openEuler aarch64 (310p)
- openEuler aarch64 (910b, ACL Graph)

opencl: add general Q6_K mm and Q4_K mv (#19347)
- opencl: add general q6_k mm
- opencl: refine condition for q6_K mm
- opencl: add general q4_K mv
- opencl: fix whitespace
macOS/iOS:
- macOS Apple Silicon (arm64)
- macOS Intel (x64)
- iOS XCFramework
Linux:
- Ubuntu x64 (CPU)
- Ubuntu x64 (Vulkan)
- Ubuntu s390x (CPU)
Windows:
- Windows x64 (CPU)
- Windows arm64 (CPU)
- Windows x64 (CUDA 12) - CUDA 12.4 DLLs
- Windows x64 (CUDA 13) - CUDA 13.1 DLLs
- Windows x64 (Vulkan)
- Windows x64 (SYCL)
- Windows x64 (HIP)
openEuler:
- openEuler x86 (310p)
- openEuler x86 (910b, ACL Graph)
- openEuler aarch64 (310p)
- openEuler aarch64 (910b, ACL Graph)

llama : refactor sampling_info to use buffer_view template (#19368)
- llama : refactor sampling_info to use buffer_view template
This commit updates the sampling_info struct in llama-context to use a
buffer_view template for the logits, probs, sampled tokens, and
candidates buffers.
The motivation for this is to simplify the code, improve type safety
and readability.
macOS/iOS:
- macOS Apple Silicon (arm64)
- macOS Intel (x64)
- iOS XCFramework
Linux:
- Ubuntu x64 (CPU)
- Ubuntu x64 (Vulkan)
- Ubuntu s390x (CPU)
Windows:
- Windows x64 (CPU)
- Windows arm64 (CPU)
- Windows x64 (CUDA 12) - CUDA 12.4 DLLs
- Windows x64 (CUDA 13) - CUDA 13.1 DLLs
- Windows x64 (Vulkan)
- Windows x64 (SYCL)
- Windows x64 (HIP)
openEuler:
- openEuler x86 (310p)
- openEuler x86 (910b, ACL Graph)
- openEuler aarch64 (310p)
- openEuler aarch64 (910b, ACL Graph)

chat: fix case where template accepts type content only (#19419)
- chat: fix case where template accepts type content only
- rm stray log
- reuse render_message_to_json
macOS/iOS:
- macOS Apple Silicon (arm64)
- macOS Intel (x64)
- iOS XCFramework
Linux:
- Ubuntu x64 (CPU)
- Ubuntu x64 (Vulkan)
- Ubuntu s390x (CPU)
Windows:
- Windows x64 (CPU)
- Windows arm64 (CPU)
- Windows x64 (CUDA 12) - CUDA 12.4 DLLs
- Windows x64 (CUDA 13) - CUDA 13.1 DLLs
- Windows x64 (Vulkan)
- Windows x64 (SYCL)
- Windows x64 (HIP)
openEuler:
- openEuler x86 (310p)
- openEuler x86 (910b, ACL Graph)
- openEuler aarch64 (310p)
- openEuler aarch64 (910b, ACL Graph)

[Model] Qwen3.5 dense and MoE support (no vision) (#19435)
- Unified delta net handling
- Remove old methods.
- Refactor and optimize
- Adapt autoregressive version from @ymcki
- Change to decay mask approach
- Fix bad permute
- Qwen 3.5 support
- Apply suggestions from code review
Co-authored-by: Sigbjørn Skjæret sigbjorn.skjaeret@scala.com
- Further fixes
- Use inheritance, remove unneeded conts
- Not like this!
- Remove ggml.h explicit import
- Remove transformers, fix the views
- ACTUALLY fix views, make super calls explicit in conversion.
- Fix conversion again
- Remove extra ggml.h imports
Co-authored-by: Sigbjørn Skjæret sigbjorn.skjaeret@scala.com
macOS/iOS:
- macOS Apple Silicon (arm64)
- macOS Intel (x64)
- iOS XCFramework
Linux:
- Ubuntu x64 (CPU)
- Ubuntu x64 (Vulkan)
- Ubuntu s390x (CPU)
Windows:
- Windows x64 (CPU)
- Windows arm64 (CPU)
- Windows x64 (CUDA 12) - CUDA 12.4 DLLs
- Windows x64 (CUDA 13) - CUDA 13.1 DLLs
- Windows x64 (Vulkan)
- Windows x64 (SYCL)
- Windows x64 (HIP)
openEuler:
- openEuler x86 (310p)
- openEuler x86 (910b, ACL Graph)
- openEuler aarch64 (310p)
- openEuler aarch64 (910b, ACL Graph)

metal : consolidate bin kernels (#19390)
- metal : refactor bin kernels
- cont
- cont : fix cv
macOS/iOS:
- macOS Apple Silicon (arm64)
- macOS Intel (x64)
- iOS XCFramework
Linux:
- Ubuntu x64 (CPU)
- Ubuntu x64 (Vulkan)
- Ubuntu s390x (CPU)
Windows:
- Windows x64 (CPU)
- Windows arm64 (CPU)
- Windows x64 (CUDA 12) - CUDA 12.4 DLLs
- Windows x64 (CUDA 13) - CUDA 13.1 DLLs
- Windows x64 (Vulkan)
- Windows x64 (SYCL)
- Windows x64 (HIP)
openEuler:
- openEuler x86 (310p)
- openEuler x86 (910b, ACL Graph)
- openEuler aarch64 (310p)
- openEuler aarch64 (910b, ACL Graph)

model : support Step3.5-Flash (#19283)
- Support Step3.5-Flash
- fix: norm.weight + 1 (HF zero_centered=true)
- step35: simplify GGUF conversion + drop redundant rope KVs
- Address review feedback
- rename limits -> clamp
- Apply suggestions from code review
Co-authored-by: Sigbjørn Skjæret sigbjorn.skjaeret@scala.com
- Apply suggestion from @CISC
Co-authored-by: Sigbjørn Skjæret sigbjorn.skjaeret@scala.com
- rename swiglu limits -> swiglu clamp in LLM_KV
- avoid CI fail
- Apply suggestions from code review
- Apply suggestions from code review
- disabled KV shifting for LLM_ARCH_STEP35
- Apply suggestions from code review
- mistakenly removed cmath
- add model size && apply missed suggestion
- assert partial_rotary_factors
- fix CI errors:
- load freq_base_swa
Co-authored-by: lvyichen lvyichen@stepfun.com
Co-authored-by: Sigbjørn Skjæret sigbjorn.skjaeret@scala.com
macOS/iOS:
- macOS Apple Silicon (arm64)
- macOS Intel (x64)
- iOS XCFramework
Linux:
- Ubuntu x64 (CPU)
- Ubuntu x64 (Vulkan)
- Ubuntu s390x (CPU)
Windows:
- Windows x64 (CPU)
- Windows arm64 (CPU)
- Windows x64 (CUDA 12) - CUDA 12.4 DLLs
- Windows x64 (CUDA 13) - CUDA 13.1 DLLs
- Windows x64 (Vulkan)
- Windows x64 (SYCL)
- Windows x64 (HIP)
openEuler:
- openEuler x86 (310p)
- openEuler x86 (910b, ACL Graph)
- openEuler aarch64 (310p)
- openEuler aarch64 (910b, ACL Graph)

metal : adaptive CPU/GPU interleave based on number of nodes (#19369)
macOS/iOS:
- macOS Apple Silicon (arm64)
- macOS Intel (x64)
- iOS XCFramework
Linux:
- Ubuntu x64 (CPU)
- Ubuntu x64 (Vulkan)
- Ubuntu s390x (CPU)
Windows:
- Windows x64 (CPU)
- Windows arm64 (CPU)
- Windows x64 (CUDA 12) - CUDA 12.4 DLLs
- Windows x64 (CUDA 13) - CUDA 13.1 DLLs
- Windows x64 (Vulkan)
- Windows x64 (SYCL)
- Windows x64 (HIP)
openEuler:
- openEuler x86 (310p)
- openEuler x86 (910b, ACL Graph)
- openEuler aarch64 (310p)
- openEuler aarch64 (910b, ACL Graph)

vendor : add missing llama_add_compile_flags (#19322)
- add missing llama_add_compile_flags
- disable all warnings for ssl, crypto and fipsmodule
macOS/iOS:
- macOS Apple Silicon (arm64)
- macOS Intel (x64)
- iOS XCFramework
Linux:
- Ubuntu x64 (CPU)
- Ubuntu x64 (Vulkan)
- Ubuntu s390x (CPU)
Windows:
- Windows x64 (CPU)
- Windows arm64 (CPU)
- Windows x64 (CUDA 12) - CUDA 12.4 DLLs
- Windows x64 (CUDA 13) - CUDA 13.1 DLLs
- Windows x64 (Vulkan)
- Windows x64 (SYCL)
- Windows x64 (HIP)
openEuler:
- openEuler x86 (310p)
- openEuler x86 (910b, ACL Graph)
- openEuler aarch64 (310p)
- openEuler aarch64 (910b, ACL Graph)

ggml-virtgpu: make the code thread safe (#19204)
- ggml-virtgpu: regenerate_remoting.py: add the ability to deprecate a function
- ggml-virtgpu: deprecate buffer_type is_host remoting
not necessary
- ggml-virtgpu: stop using static vars as cache
The static init isn't thread safe.
- ggml-virtgpu: protect the use of the shared memory to transfer data
- ggml-virtgpu: make the remote calls thread-safe
- ggml-virtgpu: backend: don't continue if couldn't allocate the tensor memory
- ggml-virtgpu: add a cleanup function for consistency
- ggml-virtgpu: backend: don't crash if buft->iface.get_max_size is missing
- fix style and ordering
- Remove the static variable in apir_device_get_count
- ggml-virtgpu: improve the logging
- fix review minor formatting changes
macOS/iOS:
- macOS Apple Silicon (arm64)
- macOS Intel (x64)
- iOS XCFramework
Linux:
- Ubuntu x64 (CPU)
- Ubuntu x64 (Vulkan)
- Ubuntu s390x (CPU)
Windows:
- Windows x64 (CPU)
- Windows arm64 (CPU)
- Windows x64 (CUDA 12) - CUDA 12.4 DLLs
- Windows x64 (CUDA 13) - CUDA 13.1 DLLs
- Windows x64 (Vulkan)
- Windows x64 (SYCL)
- Windows x64 (HIP)
openEuler:
- openEuler x86 (310p)
- openEuler x86 (910b, ACL Graph)
- openEuler aarch64 (310p)
- openEuler aarch64 (910b, ACL Graph)

opencl: refactor some ops, concat, repeat, tanh and scale (#19226)
- opencl: refactor concat
- opencl: refactor repeat
- opencl: refactor tanh
- opencl: enable fp16 for tanh
- opencl: refactor scale
- opencl: fix unused variables
macOS/iOS:
- macOS Apple Silicon (arm64)
- macOS Intel (x64)
- iOS XCFramework
Linux:
- Ubuntu x64 (CPU)
- Ubuntu x64 (Vulkan)
- Ubuntu s390x (CPU)
Windows:
- Windows x64 (CPU)
- Windows arm64 (CPU)
- Windows x64 (CUDA 12) - CUDA 12.4 DLLs
- Windows x64 (CUDA 13) - CUDA 13.1 DLLs
- Windows x64 (Vulkan)
- Windows x64 (SYCL)
- Windows x64 (HIP)
openEuler:
- openEuler x86 (310p)
- openEuler x86 (910b, ACL Graph)
- openEuler aarch64 (310p)
- openEuler aarch64 (910b, ACL Graph)

ggml-hexagon: flash-attention and reduce-sum optimizations (#19141)
- wip
- ggml-hexagon: add vectorized dot product function for FP32 and FP16 accumulation
- ggml-hexagon: optimize dot product functions for FP16 and FP32 with new vectorized implementations
- wip
- ggml-hexagon: optimize hvx_vec_dump_f32_n and hvx_vec_reduce_sum_qf32x2 functions for improved performance
- ggml-hexagon: refactor dot product functions to use a common loading function for improved readability
- optimize vector dot product functions to use unified reduction for improved performance
- wip
- ggml-hexagon: add vectorized dot product function for FP32 and FP16 accumulation
- ggml-hexagon: optimize dot product functions for FP16 and FP32 with new vectorized implementations
- wip
- ggml-hexagon: optimize hvx_vec_dump_f32_n and hvx_vec_reduce_sum_qf32x2 functions for improved performance
- ggml-hexagon: refactor dot product functions to use a common loading function for improved readability
- optimize vector dot product functions to use unified reduction for improved performance
- hexagon: optimize reduce-sum for v75+
- hexagon: always keep row_sums in sf/fp32
- ggml-hexagon: enhance directory checks for HEXAGON_SDK_ROOT and HEXAGON_TOOLS_ROOT
- fix compiling error after rebase
Co-authored-by: Max Krasnyansky maxk@qti.qualcomm.com
macOS/iOS:
- macOS Apple Silicon (arm64)
- macOS Intel (x64)
- iOS XCFramework
Linux:
- Ubuntu x64 (CPU)
- Ubuntu x64 (Vulkan)
- Ubuntu s390x (CPU)
Windows:
- Windows x64 (CPU)
- Windows arm64 (CPU)
- Windows x64 (CUDA 12) - CUDA 12.4 DLLs
- Windows x64 (CUDA 13) - CUDA 13.1 DLLs
- Windows x64 (Vulkan)
- Windows x64 (SYCL)
- Windows x64 (HIP)
openEuler:
- openEuler x86 (310p)
- openEuler x86 (910b, ACL Graph)
- openEuler aarch64 (310p)
- openEuler aarch64 (910b, ACL Graph)

quantize: add option --tensor-type-file to llama-quantize (#18572)
- add option --tensor-type-file to llama-quantize, but it raises an error.
- add error message when file not found
- quantize: update help menu, fix CI
Signed-off-by: Aaron Teo aaron.teo1@ibm.com
Signed-off-by: Aaron Teo aaron.teo1@ibm.com
Co-authored-by: Your Name you@example.com
Co-authored-by: Aaron Teo aaron.teo1@ibm.com
macOS/iOS:
- macOS Apple Silicon (arm64)
- macOS Intel (x64)
- iOS XCFramework
Linux:
- Ubuntu x64 (CPU)
- Ubuntu x64 (Vulkan)
- Ubuntu s390x (CPU)
Windows:
- Windows x64 (CPU)
- Windows arm64 (CPU)
- Windows x64 (CUDA 12) - CUDA 12.4 DLLs
- Windows x64 (CUDA 13) - CUDA 13.1 DLLs
- Windows x64 (Vulkan)
- Windows x64 (SYCL)
- Windows x64 (HIP)
openEuler:
- openEuler x86 (310p)
- openEuler x86 (910b, ACL Graph)
- openEuler aarch64 (310p)
- openEuler aarch64 (910b, ACL Graph)

sycl: implement GGML_OP_TRI (#19089)
- sycl: implement GGML_OP_TRI
- docs: update ops.md for SYCL TRI
- docs: regenerate ops.md
- docs: update SYCL support for GGML_OP_TRI
macOS/iOS:
- macOS Apple Silicon (arm64)
- macOS Intel (x64)
- iOS XCFramework
Linux:
- Ubuntu x64 (CPU)
- Ubuntu x64 (Vulkan)
- Ubuntu s390x (CPU)
Windows:
- Windows x64 (CPU)
- Windows arm64 (CPU)
- Windows x64 (CUDA 12) - CUDA 12.4 DLLs
- Windows x64 (CUDA 13) - CUDA 13.1 DLLs
- Windows x64 (Vulkan)
- Windows x64 (SYCL)
- Windows x64 (HIP)
openEuler:
- openEuler x86 (310p)
- openEuler x86 (910b, ACL Graph)
- openEuler aarch64 (310p)
- openEuler aarch64 (910b, ACL Graph)

CUDA: refactor topk-moe to enable more models (GLM 4.7, Nemotron etc.) (#19126)
macOS/iOS:
- macOS Apple Silicon (arm64)
- macOS Intel (x64)
- iOS XCFramework
Linux:
- Ubuntu x64 (CPU)
- Ubuntu x64 (Vulkan)
- Ubuntu s390x (CPU)
Windows:
- Windows x64 (CPU)
- Windows arm64 (CPU)
- Windows x64 (CUDA 12) - CUDA 12.4 DLLs
- Windows x64 (CUDA 13) - CUDA 13.1 DLLs
- Windows x64 (Vulkan)
- Windows x64 (SYCL)
- Windows x64 (HIP)
openEuler:
- openEuler x86 (310p)
- openEuler x86 (910b, ACL Graph)
- openEuler aarch64 (310p)
- openEuler aarch64 (910b, ACL Graph)

CUDA: faster FA for GQA > 1 but not power of 2 (#19092)
macOS/iOS:
- macOS Apple Silicon (arm64)
- macOS Intel (x64)
- iOS XCFramework
Linux:
- Ubuntu x64 (CPU)
- Ubuntu x64 (Vulkan)
- Ubuntu s390x (CPU)
Windows:
- Windows x64 (CPU)
- Windows arm64 (CPU)
- Windows x64 (CUDA 12) - CUDA 12.4 DLLs
- Windows x64 (CUDA 13) - CUDA 13.1 DLLs
- Windows x64 (Vulkan)
- Windows x64 (SYCL)
- Windows x64 (HIP)
openEuler:
- openEuler x86 (310p)
- openEuler x86 (910b, ACL Graph)
- openEuler aarch64 (310p)
- openEuler aarch64 (910b, ACL Graph)

llama-fit-params: keep explicit --ctx-size 0 (#19070)
macOS/iOS:
- macOS Apple Silicon (arm64)
- macOS Intel (x64)
- iOS XCFramework
Linux:
- Ubuntu x64 (CPU)
- Ubuntu x64 (Vulkan)
- Ubuntu s390x (CPU)
Windows:
- Windows x64 (CPU)
- Windows arm64 (CPU)
- Windows x64 (CUDA 12) - CUDA 12.4 DLLs
- Windows x64 (CUDA 13) - CUDA 13.1 DLLs
- Windows x64 (Vulkan)
- Windows x64 (SYCL)
- Windows x64 (HIP)
openEuler:
- openEuler x86 (310p)
- openEuler x86 (910b, ACL Graph)
- openEuler aarch64 (310p)
- openEuler aarch64 (910b, ACL Graph)

graph : utilize ggml_build_forward_select() to avoid reallocations (#18898)
- graph : avoid branches between embedding and token inputs
- models : make deepstack graphs (e.g. Qwen3 VL) have constant topology
- ci : enable -DGGML_SCHED_NO_REALLOC=ON for server CI
- cont : pad token embeddings to n_embd_inp
macOS/iOS:
- macOS Apple Silicon (arm64)
- macOS Intel (x64)
- iOS XCFramework
Linux:
- Ubuntu x64 (CPU)
- Ubuntu x64 (Vulkan)
- Ubuntu s390x (CPU)
Windows:
- Windows x64 (CPU)
- Windows arm64 (CPU)
- Windows x64 (CUDA 12) - CUDA 12.4 DLLs
- Windows x64 (CUDA 13) - CUDA 13.1 DLLs
- Windows x64 (Vulkan)
- Windows x64 (SYCL)
- Windows x64 (HIP)
openEuler:
- openEuler x86 (310p)
- openEuler x86 (910b, ACL Graph)
- openEuler aarch64 (310p)
- openEuler aarch64 (910b, ACL Graph)

cli : load parser definition (#19031)
- cli : load parser definition
- cont : only unload if a parser is defined
macOS/iOS:
- macOS Apple Silicon (arm64)
- macOS Intel (x64)
- iOS XCFramework
Linux:
- Ubuntu x64 (CPU)
- Ubuntu x64 (Vulkan)
- Ubuntu s390x (CPU)
Windows:
- Windows x64 (CPU)
- Windows arm64 (CPU)
- Windows x64 (CUDA 12) - CUDA 12.4 DLLs
- Windows x64 (CUDA 13) - CUDA 13.1 DLLs
- Windows x64 (Vulkan)
- Windows x64 (SYCL)
- Windows x64 (HIP)
openEuler:
- openEuler x86 (310p)
- openEuler x86 (910b, ACL Graph)
- openEuler aarch64 (310p)
- openEuler aarch64 (910b, ACL Graph)

CUDA: Fix builds for older CCCL versions by ifdefing strided_iterator (#18964)
- CUDA: Fix builds for older CCCL versions by ifdefing strided_iterator
Strided iterator was added in CCCL
3.1, which is packaged into
CTK
13.1
- Unindent as per code review request
macOS/iOS:
- macOS Apple Silicon (arm64)
- macOS Intel (x64)
- iOS XCFramework
Linux:
- Ubuntu x64 (CPU)
- Ubuntu x64 (Vulkan)
- Ubuntu s390x (CPU)
Windows:
- Windows x64 (CPU)
- Windows arm64 (CPU)
- Windows x64 (CUDA 12) - CUDA 12.4 DLLs
- Windows x64 (CUDA 13) - CUDA 13.1 DLLs
- Windows x64 (Vulkan)
- Windows x64 (SYCL)
- Windows x64 (HIP)
openEuler:
- openEuler x86 (310p)
- openEuler x86 (910b, ACL Graph)
- openEuler aarch64 (310p)
- openEuler aarch64 (910b, ACL Graph)

server : refactor oai_parser_opt, move it to server_chat_params (#18937)
- server_chat_params
- move chat format into CLI
- use meta whenever possible
- clean up, no more chatml fallback
macOS/iOS:
- macOS Apple Silicon (arm64)
- macOS Intel (x64)
- iOS XCFramework
Linux:
- Ubuntu x64 (CPU)
- Ubuntu x64 (Vulkan)
- Ubuntu s390x (CPU)
Windows:
- Windows x64 (CPU)
- Windows arm64 (CPU)
- Windows x64 (CUDA 12) - CUDA 12.4 DLLs
- Windows x64 (CUDA 13) - CUDA 13.1 DLLs
- Windows x64 (Vulkan)
- Windows x64 (SYCL)
- Windows x64 (HIP)
openEuler:
- openEuler x86 (310p)
- openEuler x86 (910b, ACL Graph)
- openEuler aarch64 (310p)
- openEuler aarch64 (910b, ACL Graph)

llama : Extend fallback, fix fileno for dio file, exclude case that mmap uses dio file (#18887)
macOS/iOS:
- macOS Apple Silicon (arm64)
- macOS Intel (x64)
- iOS XCFramework
Linux:
- Ubuntu x64 (CPU)
- Ubuntu x64 (Vulkan)
- Ubuntu s390x (CPU)
Windows:
- Windows x64 (CPU)
- Windows arm64 (CPU)
- Windows x64 (CUDA 12) - CUDA 12.4 DLLs
- Windows x64 (CUDA 13) - CUDA 13.1 DLLs
- Windows x64 (Vulkan)
- Windows x64 (SYCL)
- Windows x64 (HIP)
openEuler:
- openEuler x86 (310p)
- openEuler x86 (910b, ACL Graph)
- openEuler aarch64 (310p)
- openEuler aarch64 (910b, ACL Graph)

tests : add test-jinja -py option for cross-checking (#18906)
- tests : add test-jinja -py option or cross-checking
- Update tests/test-jinja.cpp
Co-authored-by: Sigbjørn Skjæret sigbjorn.skjaeret@scala.com
- fix + add source
- SandboxedEnvironment
- fix array.map case
Co-authored-by: Sigbjørn Skjæret sigbjorn.skjaeret@scala.com
macOS/iOS:
- macOS Apple Silicon (arm64)
- macOS Intel (x64)
- iOS XCFramework
Linux:
- Ubuntu x64 (CPU)
- Ubuntu x64 (Vulkan)
- Ubuntu s390x (CPU)
Windows:
- Windows x64 (CPU)
- Windows arm64 (CPU)
- Windows x64 (CUDA 12) - CUDA 12.4 DLLs
- Windows x64 (CUDA 13) - CUDA 13.1 DLLs
- Windows x64 (Vulkan)
- Windows x64 (SYCL)
- Windows x64 (HIP)
openEuler:
- openEuler x86 (310p)
- openEuler x86 (910b, ACL Graph)
- openEuler aarch64 (310p)
- openEuler aarch64 (910b, ACL Graph)

vulkan: preprocess mul_mat_id experts and discard workgroups more quickly (#18352)
Run a preprocess to count how many times each expert is used, and use this to
quickly discard workgroups that aren't needed.
macOS/iOS:
- macOS Apple Silicon (arm64)
- macOS Intel (x64)
- iOS XCFramework
Linux:
- Ubuntu x64 (CPU)
- Ubuntu x64 (Vulkan)
- Ubuntu s390x (CPU)
Windows:
- Windows x64 (CPU)
- Windows arm64 (CPU)
- Windows x64 (CUDA 12) - CUDA 12.4 DLLs
- Windows x64 (CUDA 13) - CUDA 13.1 DLLs
- Windows x64 (Vulkan)
- Windows x64 (SYCL)
- Windows x64 (HIP)
openEuler:
- openEuler x86 (310p)
- openEuler x86 (910b)
- openEuler aarch64 (310p)
- openEuler aarch64 (910b)

CANN: implement the SSM_CONV operator (#17737)
- CANN: implement SSM_CONV operator
Co-authored-by: Aleksei Lobanov, zeromarblectm@gmail.com
Co-authored-by: Sujin Kang, waterjin326@gmail.com
- CANN: remove custom error limit for SSM_CONV
- CANN: merge SSM_CONV tensor shape/strides into one line
Co-authored-by: Sujin Kang, waterjin326@gmail.com
macOS/iOS:
- macOS Apple Silicon (arm64)
- macOS Intel (x64)
- iOS XCFramework
Linux:
- Ubuntu x64 (CPU)
- Ubuntu x64 (Vulkan)
- Ubuntu s390x (CPU)
Windows:
- Windows x64 (CPU)
- Windows arm64 (CPU)
- Windows x64 (CUDA 12) - CUDA 12.4 DLLs
- Windows x64 (CUDA 13) - CUDA 13.1 DLLs
- Windows x64 (Vulkan)
- Windows x64 (SYCL)
- Windows x64 (HIP)
openEuler:
- openEuler x86 (310p)
- openEuler x86 (910b)
- openEuler aarch64 (310p)
- openEuler aarch64 (910b)

model : support for LlamaBidirectionalModel architecture (#18220)
- model: llama-embed-nemotron
- minor: python lint
- changed arch-name
- templated llm_build_llama to be used for both llama and llama-embed arch
macOS/iOS:
- macOS Apple Silicon (arm64)
- macOS Intel (x64)
- iOS XCFramework
Linux:
- Ubuntu x64 (CPU)
- Ubuntu x64 (Vulkan)
- Ubuntu s390x (CPU)
Windows:
- Windows x64 (CPU)
- Windows arm64 (CPU)
- Windows x64 (CUDA 12) - CUDA 12.4 DLLs
- Windows x64 (CUDA 13) - CUDA 13.1 DLLs
- Windows x64 (Vulkan)
- Windows x64 (SYCL)
- Windows x64 (HIP)
openEuler:
- openEuler x86 (310p)
- openEuler x86 (910b)
- openEuler aarch64 (310p)
- openEuler aarch64 (910b)

server: return_progress to also report 0% processing state (#18305)
macOS/iOS:
- macOS Apple Silicon (arm64)
- macOS Intel (x64)
- iOS XCFramework
Linux:
- Ubuntu x64 (CPU)
- Ubuntu x64 (Vulkan)
- Ubuntu s390x (CPU)
Windows:
- Windows x64 (CPU)
- Windows arm64 (CPU)
- Windows x64 (CUDA 12) - CUDA 12.4 DLLs
- Windows x64 (CUDA 13) - CUDA 13.1 DLLs
- Windows x64 (Vulkan)
- Windows x64 (SYCL)
- Windows x64 (HIP)
openEuler:
- openEuler x86 (310p)
- openEuler x86 (910b)
- openEuler aarch64 (310p)
- openEuler aarch64 (910b)

model : fix div-by-zero for Nemotron V2 (#18309)
- llama-model : fix Nemotron V2 crash by moving MoE parameters calculation
- remove whitespace
Co-authored-by: Sigbjørn Skjæret sigbjorn.skjaeret@scala.com
macOS/iOS:
- macOS Apple Silicon (arm64)
- macOS Intel (x64)
- iOS XCFramework
Linux:
- Ubuntu x64 (CPU)
- Ubuntu x64 (Vulkan)
- Ubuntu s390x (CPU)
Windows:
- Windows x64 (CPU)
- Windows arm64 (CPU)
- Windows x64 (CUDA 12) - CUDA 12.4 DLLs
- Windows x64 (CUDA 13) - CUDA 13.1 DLLs
- Windows x64 (Vulkan)
- Windows x64 (SYCL)
- Windows x64 (HIP)
openEuler:
- openEuler x86 (310p)
- openEuler x86 (910b)
- openEuler aarch64 (310p)
- openEuler aarch64 (910b)

vulkan: Implement set_tensor_async and the event interfaces (#18047)
The goal is to enable the async loading code paths in
llama_model_loader::load_all_data, originally from #7896. This works and the
loads themselves are faster, but with host visible vidmem I think the cost of
allocating/mapping vidmem moves and becomes more expensive, and I don't see a
benefit by default. But with GGML_VK_DISABLE_HOST_VISIBLE_VIDMEM=1 I do see a
significant improvement in model loading time.
macOS/iOS:
- macOS Apple Silicon (arm64)
- macOS Intel (x64)
- iOS XCFramework
Linux:
- Ubuntu x64 (CPU)
- Ubuntu x64 (Vulkan)
- Ubuntu s390x (CPU)
Windows:
- Windows x64 (CPU)
- Windows arm64 (CPU)
- Windows x64 (CUDA 12) - CUDA 12.4 DLLs
- Windows x64 (CUDA 13) - CUDA 13.1 DLLs
- Windows x64 (Vulkan)
- Windows x64 (SYCL)
- Windows x64 (HIP)
openEuler:
- openEuler x86 (310p)
- openEuler x86 (910b)
- openEuler aarch64 (310p)
- openEuler aarch64 (910b)

common : reorganize includes to prioritize vendored deps (#18222)
macOS/iOS:
- macOS Apple Silicon (arm64)
- macOS Intel (x64)
- iOS XCFramework
Linux:
- Ubuntu x64 (CPU)
- Ubuntu x64 (Vulkan)
- Ubuntu s390x (CPU)
Windows:
- Windows x64 (CPU)
- Windows arm64 (CPU)
- Windows x64 (CUDA 12) - CUDA 12.4 DLLs
- Windows x64 (CUDA 13) - CUDA 13.1 DLLs
- Windows x64 (Vulkan)
- Windows x64 (SYCL)
- Windows x64 (HIP)
openEuler:
- openEuler x86 (310p)
- openEuler x86 (910b)
- openEuler aarch64 (310p)
- openEuler aarch64 (910b)

Warning
Release Format Update: Linux releases will soon use .tar.gz archives instead of .zip. Please make the necessary changes to your deployment scripts.
model : add ASR support for LFM2-Audio-1.5B (conformer) (#18106)
- ASR with LFM2-Audio-1.5B
- Set rope_theta
- Fix comment
- Remove rope_theta setting
- Address PR feedback
- rename functions to conformer
- remove some redundant ggml_cont
- fix missing tensor
- add prefix "a." for conv tensors
- remove redundant reshape
- clean up
- add test model
Co-authored-by: Tarek Dakhran tarek@liquid.ai
macOS/iOS:
- macOS Apple Silicon (arm64)
- macOS Intel (x64)
- iOS XCFramework
Linux:
- Ubuntu x64 (CPU)
- Ubuntu x64 (Vulkan)
- Ubuntu s390x (CPU)
Windows:
- Windows x64 (CPU)
- Windows arm64 (CPU)
- Windows x64 (CUDA 12)
- Windows x64 (CUDA 13)
- Windows x64 (Vulkan)
- Windows x64 (SYCL)
- Windows x64 (HIP)
openEuler:
- openEuler x86 (310p)
- openEuler x86 (910b)
- openEuler aarch64 (310p)
- openEuler aarch64 (910b)

Warning
Release Format Update: Linux releases will soon use .tar.gz archives instead of .zip. Please make the necessary changes to your deployment scripts.
llama-fit-params: force disable mlock (#18103)
macOS/iOS:
- macOS Apple Silicon (arm64)
- macOS Intel (x64)
- iOS XCFramework
Linux:
- Ubuntu x64 (CPU)
- Ubuntu x64 (Vulkan)
- Ubuntu s390x (CPU)
Windows:
- Windows x64 (CPU)
- Windows arm64 (CPU)
- Windows x64 (CUDA 12)
- Windows x64 (CUDA 13)
- Windows x64 (Vulkan)
- Windows x64 (SYCL)
- Windows x64 (HIP)
openEuler:
- openEuler x86 (310p)
- openEuler x86 (910b)
- openEuler aarch64 (310p)
- openEuler aarch64 (910b)

Warning
Release Format Update: Linux releases will soon use .tar.gz archives instead of .zip. Please make the necessary changes to your deployment scripts.
ggml-hexagon: mm for mtmd (#17894)
- feat: add run_mtmd script for hexagon
- fix: fix issue in fp16xfp32 mm
- fix: remove opt_experiment for fp16xfp32 mm
- fix: ggml-hexagon: matmul fp16xfp32 support non-contigious src0
- fix: fix syntax check for run-mtmd.sh for cli
macOS/iOS:
- macOS Apple Silicon (arm64)
- macOS Intel (x64)
- iOS XCFramework
Linux:
- Ubuntu x64 (CPU)
- Ubuntu x64 (Vulkan)
- Ubuntu s390x (CPU)
Windows:
- Windows x64 (CPU)
- Windows arm64 (CPU)
- Windows x64 (CUDA 12)
- Windows x64 (CUDA 13)
- Windows x64 (Vulkan)
- Windows x64 (SYCL)
- Windows x64 (HIP)
openEuler:
- openEuler x86 (310p)
- openEuler x86 (910b)
- openEuler aarch64 (310p)
- openEuler aarch64 (910b)

Warning
Release Format Update: Linux releases will soon use .tar.gz archives instead of .zip. Please make the necessary changes to your deployment scripts.
[SYCL] Support gpt-oss by OPs add-id, mul_mat for mxfp4, swiglu_oai (#17826)
- support gpt-oss GPU by OP add-id, mul_mat for mxfp4, swiglu_oai, fix warning
- fix fault ut case, update ops.md
- rebase, fix format issue
macOS/iOS:
- macOS Apple Silicon (arm64)
- macOS Intel (x64)
- iOS XCFramework
Linux:
- Ubuntu x64 (CPU)
- Ubuntu x64 (Vulkan)
- Ubuntu s390x (CPU)
Windows:
- Windows x64 (CPU)
- Windows arm64 (CPU)
- Windows x64 (CUDA 12)
- Windows x64 (CUDA 13)
- Windows x64 (Vulkan)
- Windows x64 (SYCL)
- Windows x64 (HIP)
openEuler:
- openEuler x86 (310p)
- openEuler x86 (910b)
- openEuler aarch64 (310p)
- openEuler aarch64 (910b)

Warning
Release Format Update: Linux releases will soon use .tar.gz archives instead of .zip. Please make the necessary changes to your deployment scripts.
server-models.cpp: add missing (#18000)
Fixes: #17999
macOS/iOS:
- macOS Apple Silicon (arm64)
- macOS Intel (x64)
- iOS XCFramework
Linux:
- Ubuntu x64 (CPU)
- Ubuntu x64 (Vulkan)
- Ubuntu s390x (CPU)
Windows:
- Windows x64 (CPU)
- Windows arm64 (CPU)
- Windows x64 (CUDA 12)
- Windows x64 (CUDA 13)
- Windows x64 (Vulkan)
- Windows x64 (SYCL)
- Windows x64 (HIP)
openEuler:
- openEuler x86 (310p)
- openEuler x86 (910b)
- openEuler aarch64 (310p)
- openEuler aarch64 (910b)

Warning
Release Format Update: Linux releases will soon use .tar.gz archives instead of .zip. Please make the necessary changes to your deployment scripts.
common: support negated args (#17919)
- args: support negated args
- update docs
- fix typo
- add more neg options
- Apply suggestions from code review
Co-authored-by: Sigbjørn Skjæret sigbjorn.skjaeret@scala.com
- rm duplicated arg
- fix LLAMA_ARG_NO_HOST
- add test
Co-authored-by: Sigbjørn Skjæret sigbjorn.skjaeret@scala.com
macOS/iOS:
- macOS Apple Silicon (arm64)
- macOS Intel (x64)
- iOS XCFramework
Linux:
- Ubuntu x64 (CPU)
- Ubuntu x64 (Vulkan)
- Ubuntu s390x (CPU)
Windows:
- Windows x64 (CPU)
- Windows arm64 (CPU)
- Windows x64 (CUDA 12)
- Windows x64 (CUDA 13)
- Windows x64 (Vulkan)
- Windows x64 (SYCL)
- Windows x64 (HIP)
openEuler:
- openEuler x86 (310p)
- openEuler x86 (910b)
- openEuler aarch64 (310p)
- openEuler aarch64 (910b)

Warning
Release Format Update: Linux releases will soon use .tar.gz archives instead of .zip. Please make the necessary changes to your deployment scripts.
SOLVE_TRI extension to more dimensions (#17793)
- Extended TRI
- Fix whitespace
- chore: update webui build output
- Just use cuBLAS for everything...
- Merge both versions
- Remove incorrect imports causing failures for CI
- Still failing... remove all direct cublas imports and rely on common imports from "common.cuh"
- Defines for hipBlas
- Aaaand MUSA defines...
- I hate this job...
- Stupid typo...
- Update ggml/src/ggml-cuda/solve_tri.cu
Co-authored-by: Johannes Gäßler johannesg@5d6.de
Co-authored-by: Johannes Gäßler johannesg@5d6.de
macOS/iOS:
- macOS Apple Silicon (arm64)
- macOS Intel (x64)
- iOS XCFramework
Linux:
- Ubuntu x64 (CPU)
- Ubuntu x64 (Vulkan)
- Ubuntu s390x (CPU)
Windows:
- Windows x64 (CPU)
- Windows arm64 (CPU)
- Windows x64 (CUDA 12)
- Windows x64 (CUDA 13)
- Windows x64 (Vulkan)
- Windows x64 (SYCL)
- Windows x64 (HIP)

Warning
Release Format Update: Linux releases will soon use .tar.gz archives instead of .zip. Please make the necessary changes to your deployment scripts.
ggml-hexagon: fix rope failure at test-backend-ops (#17565)
- fix test failure
- fix: correct scaling calculations in rope_cache_init
- fix: optimize element copying in rope_hex_f32 using memcpy
- fix: optimize loop boundaries in rope_hex_f32 for better performance
- feat: add profiling macros for performance measurement in operations
macOS/iOS:
- macOS Apple Silicon (arm64)
- macOS Intel (x64)
- iOS XCFramework
Linux:
- Ubuntu x64 (CPU)
- Ubuntu x64 (Vulkan)
- Ubuntu s390x (CPU)
Windows:
- Windows x64 (CPU)
- Windows arm64 (CPU)
- Windows x64 (CUDA 12)
- Windows x64 (CUDA 13)
- Windows x64 (Vulkan)
- Windows x64 (SYCL)
- Windows x64 (HIP)

Warning
Release Format Update: Linux releases will soon use .tar.gz archives instead of .zip. Please make the necessary changes to your deployment scripts.
model : support Rnj-1 (#17811)
- add support for rnj1
- refactor gemma3 to support rnj-1
- address review comments
macOS/iOS:
- macOS Apple Silicon (arm64)
- macOS Intel (x64)
- iOS XCFramework
Linux:
- Ubuntu x64 (CPU)
- Ubuntu x64 (Vulkan)
- Ubuntu s390x (CPU)
Windows:
- Windows x64 (CPU)
- Windows arm64 (CPU)
- Windows x64 (CUDA 12)
- Windows x64 (CUDA 13)
- Windows x64 (Vulkan)
- Windows x64 (SYCL)
- Windows x64 (HIP)

Warning
Release Format Update: Linux releases will soon use .tar.gz archives instead of .zip. Please make the necessary changes to your deployment scripts.
model: add llama 4 scaling for mistral-large (deepseek arch) (#17744)
macOS/iOS:
- macOS Apple Silicon (arm64)
- macOS Intel (x64)
- iOS XCFramework
Linux:
- Ubuntu x64 (CPU)
- Ubuntu x64 (Vulkan)
- Ubuntu s390x (CPU)
Windows:
- Windows x64 (CPU)
- Windows arm64 (CPU)
- Windows x64 (CUDA 12)
- Windows x64 (CUDA 13)
- Windows x64 (Vulkan)
- Windows x64 (SYCL)
- Windows x64 (HIP)

Warning
Release Format Update: Linux releases will soon use .tar.gz archives instead of .zip. Please make the necessary changes to your deployment scripts.
common : change --color to accept on/off/auto, default to auto (#17827)
macOS/iOS:
- macOS Apple Silicon (arm64)
- macOS Intel (x64)
- iOS XCFramework
Linux:
- Ubuntu x64 (CPU)
- Ubuntu x64 (Vulkan)
- Ubuntu s390x (CPU)
Windows:
- Windows x64 (CPU)
- Windows arm64 (CPU)
- Windows x64 (CUDA)
- Windows x64 (Vulkan)
- Windows x64 (SYCL)
- Windows x64 (HIP)

Warning
Release Format Update: Linux releases will soon use .tar.gz archives instead of .zip. Please make the necessary changes to your deployment scripts.
HIP : fix RDNA4 build (#17792)
macOS/iOS:
- macOS Apple Silicon (arm64)
- macOS Intel (x64)
- iOS XCFramework
Linux:
- Ubuntu x64 (CPU)
- Ubuntu x64 (Vulkan)
- Ubuntu s390x (CPU)
Windows:
- Windows x64 (CPU)
- Windows arm64 (CPU)
- Windows x64 (CUDA)
- Windows x64 (Vulkan)
- Windows x64 (SYCL)
- Windows x64 (HIP)

Warning
Release Format Update: Linux releases will soon use .tar.gz archives instead of .zip. Please make the necessary changes to your deployment scripts.
macOS/iOS:
- macOS Apple Silicon (arm64)
- macOS Intel (x64)
- iOS XCFramework
Linux:
- Ubuntu x64 (CPU)
- Ubuntu x64 (Vulkan)
- Ubuntu s390x (CPU)
Windows:
- Windows x64 (CPU)
- Windows arm64 (CPU)
- Windows x64 (CUDA)
- Windows x64 (Vulkan)
- Windows x64 (SYCL)
- Windows x64 (HIP)
openEuler:
- openEuler x86 (310p)
- openEuler x86 (910b)
- openEuler aarch64 (310p)
- openEuler aarch64 (910b)
release: fix duplicate libs, store symbolic links (#17299)

server: Substitute rerank placeholder from the original template only. (#30864)
Website:
- https://llama.app
Attestations:
- https://github.com/ggml-org/llama.cpp/attestations/58867720
macOS/iOS:
- macOS Apple Silicon (arm64)
- macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED
- macOS Intel (x64)
- iOS XCFramework
Linux:
- Ubuntu x64 (CPU)
- Ubuntu arm64 (CPU)
- Ubuntu s390x (CPU)
- Ubuntu x64 (Vulkan)
- Ubuntu arm64 (Vulkan)
- Ubuntu x64 (CUDA 12) - CUDA 12.8 libraries
- Ubuntu x64 (CUDA 13) - CUDA 13.4 libraries
- Ubuntu arm64 (CUDA 13) - CUDA 13.4 libraries
- Ubuntu x64 (ROCm 10.0)
- Ubuntu x64 (OpenVINO)
- Ubuntu x64 (SYCL FP32)
- Ubuntu x64 (SYCL FP16)
- Linux arm64 (Snapdragon: CPU, Adreno GPU, Hexagon NPU) - setup guide
Android:
- Android arm64 (CPU)
- Android arm64 (Snapdragon: CPU, Adreno GPU, Hexagon NPU) - setup guide
Windows:
- Windows x64 (CPU)
- Windows arm64 (CPU)
- Windows arm64 (OpenCL Adreno)
- Windows x64 (CUDA 12) - CUDA 12.4 DLLs
- Windows x64 (CUDA 13) - CUDA 13.4 DLLs
- Windows arm64 (CUDA 13) - CUDA 13.4 DLLs
- Windows x64 (Vulkan)
- Windows arm64 (Vulkan)
- Windows x64 (OpenVINO)
- Windows x64 (SYCL)
- Windows x64 (ROCm 10.0)
openEuler:
- DISABLED
- openEuler x86 (310p)
- openEuler x86 (910b, ACL Graph)
- openEuler aarch64 (310p)
- openEuler aarch64 (910b, ACL Graph)
UI:
- UI

opencl: add F32-to-I32 ARGMAX (#30897)
- opencl: add F32-to-I32 ARGMAX
Assisted-by: OpenCode
- opencl: init to 0 to be consistent with cpu
Co-authored-by: Li He lih@qti.qualcomm.com
Website:
- https://llama.app
Attestations:
- https://github.com/ggml-org/llama.cpp/attestations/58459449
macOS/iOS:
- macOS Apple Silicon (arm64)
- macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED
- macOS Intel (x64)
- iOS XCFramework
Linux:
- Ubuntu x64 (CPU)
- Ubuntu arm64 (CPU)
- Ubuntu s390x (CPU)
- Ubuntu x64 (Vulkan)
- Ubuntu arm64 (Vulkan)
- Ubuntu x64 (CUDA 12) - CUDA 12.8 libraries
- Ubuntu x64 (CUDA 13) - CUDA 13.4 libraries
- Ubuntu arm64 (CUDA 13) - CUDA 13.4 libraries
- Ubuntu x64 (ROCm 10.0)
- Ubuntu x64 (OpenVINO)
- Ubuntu x64 (SYCL FP32)
- Ubuntu x64 (SYCL FP16)
- Linux arm64 (Snapdragon: CPU, Adreno GPU, Hexagon NPU) - setup guide
Android:
- Android arm64 (CPU)
- Android arm64 (Snapdragon: CPU, Adreno GPU, Hexagon NPU) - setup guide
Windows:
- Windows x64 (CPU)
- Windows arm64 (CPU)
- Windows arm64 (OpenCL Adreno)
- Windows x64 (CUDA 12) - CUDA 12.4 DLLs
- Windows x64 (CUDA 13) - CUDA 13.4 DLLs
- Windows arm64 (CUDA 13) - CUDA 13.4 DLLs
- Windows x64 (Vulkan)
- Windows arm64 (Vulkan)
- Windows x64 (OpenVINO)
- Windows x64 (SYCL)
- Windows x64 (ROCm 10.0)
openEuler:
- DISABLED
- openEuler x86 (310p)
- openEuler x86 (910b, ACL Graph)
- openEuler aarch64 (310p)
- openEuler aarch64 (910b, ACL Graph)
UI:
- UI

server : fix usage.completion_tokens undercount with n > 1 (#29486)
Assisted-by: Copilot
Website:
- https://llama.app
Attestations:
- https://github.com/ggml-org/llama.cpp/attestations/58070419
macOS/iOS:
- macOS Apple Silicon (arm64)
- macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED
- macOS Intel (x64)
- iOS XCFramework
Linux:
- Ubuntu x64 (CPU)
- Ubuntu arm64 (CPU)
- Ubuntu s390x (CPU)
- Ubuntu x64 (Vulkan)
- Ubuntu arm64 (Vulkan)
- Ubuntu x64 (CUDA 12) - CUDA 12.8 libraries
- Ubuntu x64 (CUDA 13) - CUDA 13.4 libraries
- Ubuntu arm64 (CUDA 13) - CUDA 13.4 libraries
- Ubuntu x64 (ROCm 10.0)
- Ubuntu x64 (OpenVINO)
- Ubuntu x64 (SYCL FP32)
- Ubuntu x64 (SYCL FP16)
- Linux arm64 (Snapdragon: CPU, Adreno GPU, Hexagon NPU) - setup guide
Android:
- Android arm64 (CPU)
- Android arm64 (Snapdragon: CPU, Adreno GPU, Hexagon NPU) - setup guide
Windows:
- Windows x64 (CPU)
- Windows arm64 (CPU)
- Windows arm64 (OpenCL Adreno)
- Windows x64 (CUDA 12) - CUDA 12.4 DLLs
- Windows x64 (CUDA 13) - CUDA 13.4 DLLs
- Windows arm64 (CUDA 13) - CUDA 13.4 DLLs
- Windows x64 (Vulkan)
- Windows arm64 (Vulkan)
- Windows x64 (OpenVINO)
- Windows x64 (SYCL)
- Windows x64 (ROCm 10.0)
openEuler:
- DISABLED
- openEuler x86 (310p)
- openEuler x86 (910b, ACL Graph)
- openEuler aarch64 (310p)
- openEuler aarch64 (910b, ACL Graph)
UI:
- UI

sycl : fix get_rows on reordered quantized weights (#30430)
Co-authored-by: Sam sam@garagellm.tail7dd858.ts.net
Website:
- https://llama.app
Attestations:
- https://github.com/ggml-org/llama.cpp/attestations/57598742
macOS/iOS:
- macOS Apple Silicon (arm64)
- macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED
- macOS Intel (x64)
- iOS XCFramework
Linux:
- Ubuntu x64 (CPU)
- Ubuntu arm64 (CPU)
- Ubuntu s390x (CPU)
- Ubuntu x64 (Vulkan)
- Ubuntu arm64 (Vulkan)
- Ubuntu x64 (CUDA 12) - CUDA 12.8 libraries
- Ubuntu x64 (CUDA 13) - CUDA 13.4 libraries
- Ubuntu arm64 (CUDA 13) - CUDA 13.4 libraries
- Ubuntu x64 (ROCm 10.0)
- Ubuntu x64 (OpenVINO)
- Ubuntu x64 (SYCL FP32)
- Ubuntu x64 (SYCL FP16)
- Linux arm64 (Snapdragon: CPU, Adreno GPU, Hexagon NPU) - setup guide
Android:
- Android arm64 (CPU)
- Android arm64 (Snapdragon: CPU, Adreno GPU, Hexagon NPU) - setup guide
Windows:
- Windows x64 (CPU)
- Windows arm64 (CPU)
- Windows arm64 (OpenCL Adreno)
- Windows x64 (CUDA 12) - CUDA 12.4 DLLs
- Windows x64 (CUDA 13) - CUDA 13.4 DLLs
- Windows arm64 (CUDA 13) - CUDA 13.4 DLLs
- Windows x64 (Vulkan)
- Windows arm64 (Vulkan)
- Windows x64 (OpenVINO)
- Windows x64 (SYCL)
- Windows x64 (ROCm 10.0)
openEuler:
- DISABLED
- openEuler x86 (310p)
- openEuler x86 (910b, ACL Graph)
- openEuler aarch64 (310p)
- openEuler aarch64 (910b, ACL Graph)
UI:
- UI

hexagon: FLASH_ATTN_EXT improvements for longer context and SWA models (#30731)
- hex-fa: support for masked block skipping to reduce DMA fetching
- hex-fa: finetuning the hmx->hvx crossover thresholds (boosting gemma-4)
- hex-fa: update hmx gate to account for mdev.count
Website:
- https://llama.app
Attestations:
- https://github.com/ggml-org/llama.cpp/attestations/57234765
macOS/iOS:
- macOS Apple Silicon (arm64)
- macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED
- macOS Intel (x64)
- iOS XCFramework
Linux:
- Ubuntu x64 (CPU)
- Ubuntu arm64 (CPU)
- Ubuntu s390x (CPU)
- Ubuntu x64 (Vulkan)
- Ubuntu arm64 (Vulkan)
- Ubuntu x64 (CUDA 12) - CUDA 12.8 libraries
- Ubuntu x64 (CUDA 13) - CUDA 13.4 libraries
- Ubuntu arm64 (CUDA 13) - CUDA 13.4 libraries
- Ubuntu x64 (ROCm 10.0)
- Ubuntu x64 (OpenVINO)
- Ubuntu x64 (SYCL FP32)
- Ubuntu x64 (SYCL FP16)
- Linux arm64 (Snapdragon: CPU, Adreno GPU, Hexagon NPU) - setup guide
Android:
- Android arm64 (CPU)
- Android arm64 (Snapdragon: CPU, Adreno GPU, Hexagon NPU) - setup guide
Windows:
- Windows x64 (CPU)
- Windows arm64 (CPU)
- Windows arm64 (OpenCL Adreno)
- Windows x64 (CUDA 12) - CUDA 12.4 DLLs
- Windows x64 (CUDA 13) - CUDA 13.4 DLLs
- Windows arm64 (CUDA 13) - CUDA 13.4 DLLs
- Windows x64 (Vulkan)
- Windows arm64 (Vulkan)
- Windows x64 (OpenVINO)
- Windows x64 (SYCL)
- Windows x64 (ROCm 10.0)
openEuler:
- DISABLED
- openEuler x86 (310p)
- openEuler x86 (910b, ACL Graph)
- openEuler aarch64 (310p)
- openEuler aarch64 (910b, ACL Graph)
UI:
- UI

Restore ESIMD kernels on FFN path (#30239)
- Reenable ESIMD on the FFN path
Signed-off-by: Todd Malsbary todd.malsbary@intel.com
- Extend ESIMD fusion on FFN path to include Q8_0
Signed-off-by: Todd Malsbary todd.malsbary@intel.com
- Remove comment explicitly referencing ESIMD in test-backend-ops
Signed-off-by: Todd Malsbary todd.malsbary@intel.com
Signed-off-by: Todd Malsbary todd.malsbary@intel.com
Website:
- https://llama.app
Attestations:
- https://github.com/ggml-org/llama.cpp/attestations/57072547
macOS/iOS:
- macOS Apple Silicon (arm64)
- macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED
- macOS Intel (x64)
- iOS XCFramework
Linux:
- Ubuntu x64 (CPU)
- Ubuntu arm64 (CPU)
- Ubuntu s390x (CPU)
- Ubuntu x64 (Vulkan)
- Ubuntu arm64 (Vulkan)
- Ubuntu x64 (CUDA 12) - CUDA 12.8 libraries
- Ubuntu x64 (CUDA 13) - CUDA 13.4 libraries
- Ubuntu arm64 (CUDA 13) - CUDA 13.4 libraries
- Ubuntu x64 (ROCm 10.0)
- Ubuntu x64 (OpenVINO)
- Ubuntu x64 (SYCL FP32)
- Ubuntu x64 (SYCL FP16)
- Linux arm64 (Snapdragon: CPU, Adreno GPU, Hexagon NPU) - setup guide
Android:
- Android arm64 (CPU)
- Android arm64 (Snapdragon: CPU, Adreno GPU, Hexagon NPU) - setup guide
Windows:
- Windows x64 (CPU)
- Windows arm64 (CPU)
- Windows arm64 (OpenCL Adreno)
- Windows x64 (CUDA 12) - CUDA 12.4 DLLs
- Windows x64 (CUDA 13) - CUDA 13.4 DLLs
- Windows arm64 (CUDA 13) - CUDA 13.4 DLLs
- Windows x64 (Vulkan)
- Windows arm64 (Vulkan)
- Windows x64 (OpenVINO)
- Windows x64 (SYCL)
- Windows x64 (ROCm 10.0)
openEuler:
- DISABLED
- openEuler x86 (310p)
- openEuler x86 (910b, ACL Graph)
- openEuler aarch64 (310p)
- openEuler aarch64 (910b, ACL Graph)
UI:
- UI

sycl: fix prompt-processing regression after Q4_0/Q8_0 weight reorder (#30374)
Website:
- https://llama.app
Attestations:
- https://github.com/ggml-org/llama.cpp/attestations/56871404
macOS/iOS:
- macOS Apple Silicon (arm64)
- macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED
- macOS Intel (x64)
- iOS XCFramework
Linux:
- Ubuntu x64 (CPU)
- Ubuntu arm64 (CPU)
- Ubuntu s390x (CPU)
- Ubuntu x64 (Vulkan)
- Ubuntu arm64 (Vulkan)
- Ubuntu x64 (CUDA 12) - CUDA 12.8 libraries
- Ubuntu x64 (CUDA 13) - CUDA 13.4 libraries
- Ubuntu arm64 (CUDA 13) - CUDA 13.4 libraries
- Ubuntu x64 (ROCm 10.0)
- Ubuntu x64 (OpenVINO)
- Ubuntu x64 (SYCL FP32)
- Ubuntu x64 (SYCL FP16)
- Linux arm64 (Snapdragon: CPU, Adreno GPU, Hexagon NPU) - setup guide
Android:
- Android arm64 (CPU)
- Android arm64 (Snapdragon: CPU, Adreno GPU, Hexagon NPU) - setup guide
Windows:
- Windows x64 (CPU)
- Windows arm64 (CPU)
- Windows arm64 (OpenCL Adreno)
- Windows x64 (CUDA 12) - CUDA 12.4 DLLs
- Windows x64 (CUDA 13) - CUDA 13.4 DLLs
- Windows arm64 (CUDA 13) - CUDA 13.4 DLLs
- Windows x64 (Vulkan)
- Windows arm64 (Vulkan)
- Windows x64 (OpenVINO)
- Windows x64 (SYCL)
- Windows x64 (ROCm 10.0)
openEuler:
- DISABLED
- openEuler x86 (310p)
- openEuler x86 (910b, ACL Graph)
- openEuler aarch64 (310p)
- openEuler aarch64 (910b, ACL Graph)
UI:
- UI

hexagon: tensor repacking rework and support for tiled and flat quantized and fp weights (#30635)
- hex-repack: Remove need_repack hack and streamline the rules -- breaks GET_ROWS tests for K-Quants, will fix in the next round
Add support for GET_ROWS with tiled Q5_K
Add support for raw k-quant tensors
- hex-get-rows: vectorize raw k-quant ukernels
- hex-binary: refactor dma-loop thread functions (no need for macros, etc)
- hex-quant: move/cleanup flat and tiled dequant ukernels
- hex-repack: add support for repacking/tiling F16/F32/BF16 2D weights
- hex-get-rows: remove redundant cast
- hex-repack: proper filtering for BF16 that were leaking through during the tests
- hex-repack: streamling tiling rules (broken MM for now)
- hex-repack: fix mmid after tiling updates
- hex-repack: rename repacked to tiled in all flags/funcs/kernels/vars
- hex-mm: fix valid_rows calc in various kernels
- hex-mm: remove unused hvx_mm_nx_2d_flat
- hex-mm: cleanup and optimize hvx-tiled vec_dot_f16
- hex-mm: another pass at hvx-tiled f16 matmul
- hex-get-rows: optimize small src1
- hex-get-rows: one more pass at recovering get-rows perf regression
- hex-repack: export GGML_HEXAGON_RT_REPACK via run.py
- hex-mm-tiled: fix accuracy regression with hmx-tiled-f16 matmul
- hex-mm: fold tiled_f16 checks into the general flow
- hex-get-rows: remove dead checks for buffer_is_hexagon and tiling during supports_op
- hex-quant: proper tail handling in new dequant ukernels
- hex-get-rows: remove unused code and cleanup support checks
- hex-mm: cleanup ne1 padding/tiling checks
- hex-mm: cleanup fusion checks for tiled tensors
- hex-repack: add a little can_repack helper to reduce duplication
- hex-repack: never repack host buffers
- hex-repack: factor out repack functions into separate .h and .cpp
- hex-tensor: cleanup tensor ifaces for tiled/padded sizes
- hex-repack: update k-quant tiling comments and cleanup #defines
- hex-dcache: factor out l2/dcache dirty tracking and flushing
- hex-tensor: update docs and remove #defs duplication
- hex-tensor: remove unused/incorrect get_data interface
- hex-get-rows: cleanup vtcm layout build
- tests: disable huge MM tests
- hex-dcache: add missing header
Website:
- https://llama.app
Attestations:
- https://github.com/ggml-org/llama.cpp/attestations/56541220
macOS/iOS:
- macOS Apple Silicon (arm64)
- macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED
- macOS Intel (x64)
- iOS XCFramework
Linux:
- Ubuntu x64 (CPU)
- Ubuntu arm64 (CPU)
- Ubuntu s390x (CPU)
- Ubuntu x64 (Vulkan)
- Ubuntu arm64 (Vulkan)
- Ubuntu x64 (CUDA 12) - CUDA 12.8 libraries
- Ubuntu x64 (CUDA 13) - CUDA 13.4 libraries
- Ubuntu arm64 (CUDA 13) - CUDA 13.4 libraries
- Ubuntu x64 (ROCm 10.0)
- Ubuntu x64 (OpenVINO)
- Ubuntu x64 (SYCL FP32)
- Ubuntu x64 (SYCL FP16)
- Linux arm64 (Snapdragon: CPU, Adreno GPU, Hexagon NPU) - setup guide
Android:
- Android arm64 (CPU)
- Android arm64 (Snapdragon: CPU, Adreno GPU, Hexagon NPU) - setup guide
Windows:
- Windows x64 (CPU)
- Windows arm64 (CPU)
- Windows arm64 (OpenCL Adreno)
- Windows x64 (CUDA 12) - CUDA 12.4 DLLs
- Windows x64 (CUDA 13) - CUDA 13.4 DLLs
- Windows arm64 (CUDA 13) - CUDA 13.4 DLLs
- Windows x64 (Vulkan)
- Windows arm64 (Vulkan)
- Windows x64 (OpenVINO)
- Windows x64 (SYCL)
- Windows x64 (ROCm 10.0)
openEuler:
- DISABLED
- openEuler x86 (310p)
- openEuler x86 (910b, ACL Graph)
- openEuler aarch64 (310p)
- openEuler aarch64 (910b, ACL Graph)
UI:
- UI

sycl: IQ3 code reorder (#29107)
- sycl: persistent IQ3_S/IQ3_XXS weight reorder for SYCL decode and prefill
Add persistent reordered weight layouts for IQ3_S and IQ3_XXS. Weights
are reordered once at load time; the reordered MMVQ dot products then
walk dense super-blocks with dp4a and SWAR sign expansion instead of
gathering bits from the interleaved standard layout. Reorder-aware
dequantization feeds the batched prefill GEMMs so prompt processing
sees the same benefit.
Also harden the oneDNN build check: a missing DNNL package or a
CPU-only DNNL build now fails at configure time instead of silently
producing a degraded backend.
Measured on Intel Arc Pro B70 with Qwen3.8-27B-GSQ-RCO-IQ3_S (MTP),
-ngl 999 -b 4096 -ub 1024 -fa on:
tg256 @ 0 ctx 12.92 -> 23.54 tok/s (+82%)
tg256 @ 9,216 12.33 -> 21.69 tok/s (+76%)
tg256 @ 64,000 9.76 -> 14.91 tok/s (+53%)
pp8192 833.9 -> 833.6 tok/s (flat)
Qwen3.5-9B Q4_K_M / Q3_K_M are unchanged within noise (largest delta
-0.5% pp, tg flat), so standard quants are not affected.
The MMVQ GLU fusion widening and rms_norm+scale fusion are
intentionally not part of this change; master already carries them
via #28931.
- removing wait as per review request
- sycl : fix fusion.cpp line ending
Website:
- https://llama.app
Attestations:
- https://github.com/ggml-org/llama.cpp/attestations/56116978
macOS/iOS:
- macOS Apple Silicon (arm64)
- macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED
- macOS Intel (x64)
- iOS XCFramework
Linux:
- Ubuntu x64 (CPU)
- Ubuntu arm64 (CPU)
- Ubuntu s390x (CPU)
- Ubuntu x64 (Vulkan)
- Ubuntu arm64 (Vulkan)
- Ubuntu x64 (CUDA 12) - CUDA 12.8 libraries
- Ubuntu x64 (CUDA 13) - CUDA 13.4 libraries
- Ubuntu arm64 (CUDA 13) - CUDA 13.4 libraries
- Ubuntu x64 (ROCm 10.0)
- Ubuntu x64 (OpenVINO)
- Ubuntu x64 (SYCL FP32)
- Ubuntu x64 (SYCL FP16)
- Linux arm64 (Snapdragon: CPU, Adreno GPU, Hexagon NPU) - setup guide
Android:
- Android arm64 (CPU)
- Android arm64 (Snapdragon: CPU, Adreno GPU, Hexagon NPU) - setup guide
Windows:
- Windows x64 (CPU)
- Windows arm64 (CPU)
- Windows arm64 (OpenCL Adreno)
- Windows x64 (CUDA 12) - CUDA 12.4 DLLs
- Windows x64 (CUDA 13) - CUDA 13.4 DLLs
- Windows arm64 (CUDA 13) - CUDA 13.4 DLLs
- Windows x64 (Vulkan)
- Windows arm64 (Vulkan)
- Windows x64 (OpenVINO)
- Windows x64 (SYCL)
- Windows x64 (ROCm 10.0)
openEuler:
- DISABLED
- openEuler x86 (310p)
- openEuler x86 (910b, ACL Graph)
- openEuler aarch64 (310p)
- openEuler aarch64 (910b, ACL Graph)
UI:
- UI

webgpu: (Fix CI) fix mul_mat_id with duplicate expert ids (#30451)
- Fix mm-id of webgpu in the case of ids duplication
- formatting
- fix comments to avoid breaking up sentences in comments
Website:
- https://llama.app
Attestations:
- https://github.com/ggml-org/llama.cpp/attestations/55647479
macOS/iOS:
- macOS Apple Silicon (arm64)
- macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED
- macOS Intel (x64)
- iOS XCFramework
Linux:
- Ubuntu x64 (CPU)
- Ubuntu arm64 (CPU)
- Ubuntu s390x (CPU)
- Ubuntu x64 (Vulkan)
- Ubuntu arm64 (Vulkan)
- Ubuntu x64 (CUDA 12) - CUDA 12.8 libraries
- Ubuntu x64 (CUDA 13) - CUDA 13.4 libraries
- Ubuntu arm64 (CUDA 13) - CUDA 13.4 libraries
- Ubuntu x64 (ROCm 10.0)
- Ubuntu x64 (OpenVINO)
- Ubuntu x64 (SYCL FP32)
- Ubuntu x64 (SYCL FP16)
- Linux arm64 (Snapdragon: CPU, Adreno GPU, Hexagon NPU) - setup guide
Android:
- Android arm64 (CPU)
- Android arm64 (Snapdragon: CPU, Adreno GPU, Hexagon NPU) - setup guide
Windows:
- Windows x64 (CPU)
- Windows arm64 (CPU)
- Windows arm64 (OpenCL Adreno)
- Windows x64 (CUDA 12) - CUDA 12.4 DLLs
- Windows x64 (CUDA 13) - CUDA 13.4 DLLs
- Windows arm64 (CUDA 13) - CUDA 13.4 DLLs
- Windows x64 (Vulkan)
- Windows arm64 (Vulkan)
- Windows x64 (OpenVINO)
- Windows x64 (SYCL)
- Windows x64 (ROCm 10.0)
openEuler:
- DISABLED
- openEuler x86 (310p)
- openEuler x86 (910b, ACL Graph)
- openEuler aarch64 (310p)
- openEuler aarch64 (910b, ACL Graph)
UI:
- UI

hexagon: extend scalar DMA broadcasting support for binary ops (#30245)
- tests: cover weighted scalar broadcasts
Assisted-by: OpenCode
- ggml : support extended scalar DMA binary ops
Assisted-by: OpenCode
- hex-binary: remove all non-dma paths
- hex-binary: add support for non-contig strides and cleanup dma preable a bit
- hex-binary: cleanup the gating and simplify dma retry
- hex-geglu-erf: add a gate for F32 only, we dont support F16 for this op
- tests: cover weighted repeat broadcast
Assisted-by: OpenCode
- hex-binary: update REPEAT and COMPLEX kernels to use dma as well (missed them last time)
- hex-add-id: add dma support for src2 (idx)
Co-authored-by: Max Krasnyansky maxk@qti.qualcomm.com
Website:
- https://llama.app
Attestations:
- https://github.com/ggml-org/llama.cpp/attestations/55272788
macOS/iOS:
- macOS Apple Silicon (arm64)
- macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED
- macOS Intel (x64)
- iOS XCFramework
Linux:
- Ubuntu x64 (CPU)
- Ubuntu arm64 (CPU)
- Ubuntu s390x (CPU)
- Ubuntu x64 (Vulkan)
- Ubuntu arm64 (Vulkan)
- Ubuntu x64 (CUDA 12) - CUDA 12.8 libraries
- Ubuntu x64 (CUDA 13) - CUDA 13.4 libraries
- Ubuntu arm64 (CUDA 13) - CUDA 13.4 libraries
- Ubuntu x64 (ROCm 10.0)
- Ubuntu x64 (OpenVINO)
- Ubuntu x64 (SYCL FP32)
- Ubuntu x64 (SYCL FP16)
- Linux arm64 (Snapdragon: CPU, Adreno GPU, Hexagon NPU) - setup guide
Android:
- Android arm64 (CPU)
- Android arm64 (Snapdragon: CPU, Adreno GPU, Hexagon NPU) - setup guide
Windows:
- Windows x64 (CPU)
- Windows arm64 (CPU)
- Windows arm64 (OpenCL Adreno)
- Windows x64 (CUDA 12) - CUDA 12.4 DLLs
- Windows x64 (CUDA 13) - CUDA 13.4 DLLs
- Windows arm64 (CUDA 13) - CUDA 13.4 DLLs
- Windows x64 (Vulkan)
- Windows arm64 (Vulkan)
- Windows x64 (OpenVINO)
- Windows x64 (SYCL)
- Windows x64 (ROCm 10.0)
openEuler:
- DISABLED
- openEuler x86 (310p)
- openEuler x86 (910b, ACL Graph)
- openEuler aarch64 (310p)
- openEuler aarch64 (910b, ACL Graph)
UI:
- UI

hexagon: add IM2COL_3D (#30305)
- hexagon: add IM2COL_3D support
Assisted-by: OpenCode
- hexagon: add DMA paths for IM2COL_3D
Assisted-by: OpenCode
- hexagon: avoid scalar fp16 conversions in IM2COL
Assisted-by: OpenCode
- remove in-loop spills in pre-v81 devices
Assisted-by: OpenCode
- hex-im2col: re-write to use canonical dma dbl-buff pipeline, remove divs and very inefficient fp conversions
- hex-im2col: move kernel_params and vtcm layout precompute into the host
- hex-im2col: remove explicit tracking of number of dma-pushes
- hex-im2col: remove incorrect uint64_t casts
- hex-im2col: no need for macros for dma loops and pass compute func ptr via local context
- hex-im2col: use cursor pattern, tracing and proper n_threads handling
- hex-im2col: support non-contigue views
- hex-im2col: minor reformatting
Co-authored-by: Max Krasnyansky maxk@qti.qualcomm.com
Website:
- https://llama.app
Attestations:
- https://github.com/ggml-org/llama.cpp/attestations/54919473
macOS/iOS:
- macOS Apple Silicon (arm64)
- macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED
- macOS Intel (x64)
- iOS XCFramework
Linux:
- Ubuntu x64 (CPU)
- Ubuntu arm64 (CPU)
- Ubuntu s390x (CPU)
- Ubuntu x64 (Vulkan)
- Ubuntu arm64 (Vulkan)
- Ubuntu x64 (CUDA 12) - CUDA 12.8 libraries
- Ubuntu x64 (CUDA 13) - CUDA 13.4 libraries
- Ubuntu arm64 (CUDA 13) - CUDA 13.4 libraries
- Ubuntu x64 (ROCm 10.0)
- Ubuntu x64 (OpenVINO)
- Ubuntu x64 (SYCL FP32)
- Ubuntu x64 (SYCL FP16)
- Linux arm64 (Snapdragon: CPU, Adreno GPU, Hexagon NPU) - setup guide
Android:
- Android arm64 (CPU)
- Android arm64 (Snapdragon: CPU, Adreno GPU, Hexagon NPU) - setup guide
Windows:
- Windows x64 (CPU)
- Windows arm64 (CPU)
- Windows arm64 (OpenCL Adreno)
- Windows x64 (CUDA 12) - CUDA 12.4 DLLs
- Windows x64 (CUDA 13) - CUDA 13.4 DLLs
- Windows arm64 (CUDA 13) - CUDA 13.4 DLLs
- Windows x64 (Vulkan)
- Windows arm64 (Vulkan)
- Windows x64 (OpenVINO)
- Windows x64 (SYCL)
- Windows x64 (ROCm 10.0)
openEuler:
- DISABLED
- openEuler x86 (310p)
- openEuler x86 (910b, ACL Graph)
- openEuler aarch64 (310p)
- openEuler aarch64 (910b, ACL Graph)
UI:
- UI

server: leave a busy slot untouched when a request pins it (#30295)
A request asking for a busy id_slot still ran the prompt cache update
on that slot before being deferred. When the RAM cache held a better
match, it was loaded into the slot while another request was still
generating there, and that generation continued on the wrong context.
The busy slot is now returned as is and the request waits for it.
Website:
- https://llama.app
Attestations:
- https://github.com/ggml-org/llama.cpp/attestations/54667254
macOS/iOS:
- macOS Apple Silicon (arm64)
- macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED
- macOS Intel (x64)
- iOS XCFramework
Linux:
- Ubuntu x64 (CPU)
- Ubuntu arm64 (CPU)
- Ubuntu s390x (CPU)
- Ubuntu x64 (Vulkan)
- Ubuntu arm64 (Vulkan)
- Ubuntu x64 (CUDA 12) - CUDA 12.8 libraries
- Ubuntu x64 (CUDA 13) - CUDA 13.4 libraries
- Ubuntu arm64 (CUDA 13) - CUDA 13.4 libraries
- Ubuntu x64 (ROCm 10.0)
- Ubuntu x64 (OpenVINO)
- Ubuntu x64 (SYCL FP32)
- Ubuntu x64 (SYCL FP16)
- Linux arm64 (Snapdragon: CPU, Adreno GPU, Hexagon NPU) - setup guide
Android:
- Android arm64 (CPU)
- Android arm64 (Snapdragon: CPU, Adreno GPU, Hexagon NPU) - setup guide
Windows:
- Windows x64 (CPU)
- Windows arm64 (CPU)
- Windows arm64 (OpenCL Adreno)
- Windows x64 (CUDA 12) - CUDA 12.4 DLLs
- Windows x64 (CUDA 13) - CUDA 13.4 DLLs
- Windows arm64 (CUDA 13) - CUDA 13.4 DLLs
- Windows x64 (Vulkan)
- Windows arm64 (Vulkan)
- Windows x64 (OpenVINO)
- Windows x64 (SYCL)
- Windows x64 (ROCm 10.0)
openEuler:
- DISABLED
- openEuler x86 (310p)
- openEuler x86 (910b, ACL Graph)
- openEuler aarch64 (310p)
- openEuler aarch64 (910b, ACL Graph)
UI:
- UI

sycl : accelerate MXFP4 MoE with arithmetic decoding and weight reordering (#29809)
Website:
- https://llama.app
Attestations:
- https://github.com/ggml-org/llama.cpp/attestations/54540406
macOS/iOS:
- macOS Apple Silicon (arm64)
- macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED
- macOS Intel (x64)
- iOS XCFramework
Linux:
- Ubuntu x64 (CPU)
- Ubuntu arm64 (CPU)
- Ubuntu s390x (CPU)
- Ubuntu x64 (Vulkan)
- Ubuntu arm64 (Vulkan)
- Ubuntu x64 (CUDA 12) - CUDA 12.8 libraries
- Ubuntu x64 (CUDA 13) - CUDA 13.4 libraries
- Ubuntu arm64 (CUDA 13) - CUDA 13.4 libraries
- Ubuntu x64 (ROCm 10.0)
- Ubuntu x64 (OpenVINO)
- Ubuntu x64 (SYCL FP32)
- Ubuntu x64 (SYCL FP16)
- Linux arm64 (Snapdragon: CPU, Adreno GPU, Hexagon NPU) - setup guide
Android:
- Android arm64 (CPU)
- Android arm64 (Snapdragon: CPU, Adreno GPU, Hexagon NPU) - setup guide
Windows:
- Windows x64 (CPU)
- Windows arm64 (CPU)
- Windows arm64 (OpenCL Adreno)
- Windows x64 (CUDA 12) - CUDA 12.4 DLLs
- Windows x64 (CUDA 13) - CUDA 13.4 DLLs
- Windows arm64 (CUDA 13) - CUDA 13.4 DLLs
- Windows x64 (Vulkan)
- Windows arm64 (Vulkan)
- Windows x64 (OpenVINO)
- Windows x64 (SYCL)
- Windows x64 (ROCm 10.0)
openEuler:
- DISABLED
- openEuler x86 (310p)
- openEuler x86 (910b, ACL Graph)
- openEuler aarch64 (310p)
- openEuler aarch64 (910b, ACL Graph)
UI:
- UI

sycl : Q5_K reorder-layout MMVQ and fused GLU (#29375)
Website:
- https://llama.app
Attestations:
- https://github.com/ggml-org/llama.cpp/attestations/54173692
macOS/iOS:
- macOS Apple Silicon (arm64)
- macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED
- macOS Intel (x64)
- iOS XCFramework
Linux:
- Ubuntu x64 (CPU)
- Ubuntu arm64 (CPU)
- Ubuntu s390x (CPU)
- Ubuntu x64 (Vulkan)
- Ubuntu arm64 (Vulkan)
- Ubuntu x64 (CUDA 12) - CUDA 12.8 libraries
- Ubuntu x64 (CUDA 13) - CUDA 13.4 libraries
- Ubuntu arm64 (CUDA 13) - CUDA 13.4 libraries
- Ubuntu x64 (ROCm 10.0)
- Ubuntu x64 (OpenVINO)
- Ubuntu x64 (SYCL FP32)
- Ubuntu x64 (SYCL FP16)
- Linux arm64 (Snapdragon: CPU, Adreno GPU, Hexagon NPU) - setup guide
Android:
- Android arm64 (CPU)
- Android arm64 (Snapdragon: CPU, Adreno GPU, Hexagon NPU) - setup guide
Windows:
- Windows x64 (CPU)
- Windows arm64 (CPU)
- Windows arm64 (OpenCL Adreno)
- Windows x64 (CUDA 12) - CUDA 12.4 DLLs
- Windows x64 (CUDA 13) - CUDA 13.4 DLLs
- Windows arm64 (CUDA 13) - CUDA 13.4 DLLs
- Windows x64 (Vulkan)
- Windows arm64 (Vulkan)
- Windows x64 (OpenVINO)
- Windows x64 (SYCL)
- Windows x64 (ROCm 10.0)
openEuler:
- DISABLED
- openEuler x86 (310p)
- openEuler x86 (910b, ACL Graph)
- openEuler aarch64 (310p)
- openEuler aarch64 (910b, ACL Graph)
UI:
- UI

hexagon: enable alloc_buffer_n (#30126)
- hex-bufs: add support for alloc_buffer_n
- hex-bufs: add support for splitting large tensors into separate buffers
- hex-bufs: update GGML_HEXAGON_MBUF to accept three values dyn,static,total
- hex-bufs: bump dyn. default to 512MB since 128MB causes perf regressions with big MOEs
- hex-run: add --no-embd-offload option to simplify command lines on devices that need it
- Update scripts/snapdragon/run.py
Co-authored-by: Jhen-Jie Hong iainst0409@gmail.com
Co-authored-by: Jhen-Jie Hong iainst0409@gmail.com
Website:
- https://llama.app
Attestations:
- https://github.com/ggml-org/llama.cpp/attestations/53811782
macOS/iOS:
- macOS Apple Silicon (arm64)
- macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED
- macOS Intel (x64)
- iOS XCFramework
Linux:
- Ubuntu x64 (CPU)
- Ubuntu arm64 (CPU)
- Ubuntu s390x (CPU)
- Ubuntu x64 (Vulkan)
- Ubuntu arm64 (Vulkan)
- Ubuntu x64 (CUDA 12) - CUDA 12.8 libraries
- Ubuntu x64 (CUDA 13) - CUDA 13.4 libraries
- Ubuntu arm64 (CUDA 13) - CUDA 13.4 libraries
- Ubuntu x64 (ROCm 10.0)
- Ubuntu x64 (OpenVINO)
- Ubuntu x64 (SYCL FP32)
- Ubuntu x64 (SYCL FP16)
- Linux arm64 (Snapdragon: CPU, Adreno GPU, Hexagon NPU) - setup guide
Android:
- Android arm64 (CPU)
- Android arm64 (Snapdragon: CPU, Adreno GPU, Hexagon NPU) - setup guide
Windows:
- Windows x64 (CPU)
- Windows arm64 (CPU)
- Windows arm64 (OpenCL Adreno)
- Windows x64 (CUDA 12) - CUDA 12.4 DLLs
- Windows x64 (CUDA 13) - CUDA 13.4 DLLs
- Windows arm64 (CUDA 13) - CUDA 13.4 DLLs
- Windows x64 (Vulkan)
- Windows arm64 (Vulkan)
- Windows x64 (OpenVINO)
- Windows x64 (SYCL)
- Windows x64 (ROCm 10.0)
openEuler:
- DISABLED
- openEuler x86 (310p)
- openEuler x86 (910b, ACL Graph)
- openEuler aarch64 (310p)
- openEuler aarch64 (910b, ACL Graph)
UI:
- UI

ggml-webgpu: no dawn native features on wasi (#27069)
Website:
- https://llama.app
Attestations:
- https://github.com/ggml-org/llama.cpp/attestations/53445261
macOS/iOS:
- macOS Apple Silicon (arm64)
- macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED
- macOS Intel (x64)
- iOS XCFramework
Linux:
- Ubuntu x64 (CPU)
- Ubuntu arm64 (CPU)
- Ubuntu s390x (CPU)
- Ubuntu x64 (Vulkan)
- Ubuntu arm64 (Vulkan)
- Ubuntu x64 (CUDA 12) - CUDA 12.8 libraries
- Ubuntu x64 (CUDA 13) - CUDA 13.4 libraries
- Ubuntu arm64 (CUDA 13) - CUDA 13.4 libraries
- Ubuntu x64 (ROCm 10.0)
- Ubuntu x64 (OpenVINO)
- Ubuntu x64 (SYCL FP32)
- Ubuntu x64 (SYCL FP16)
- Linux arm64 (Snapdragon: CPU, Adreno GPU, Hexagon NPU) - setup guide
Android:
- Android arm64 (CPU)
- Android arm64 (Snapdragon: CPU, Adreno GPU, Hexagon NPU) - setup guide
Windows:
- Windows x64 (CPU)
- Windows arm64 (CPU)
- Windows arm64 (OpenCL Adreno)
- Windows x64 (CUDA 12) - CUDA 12.4 DLLs
- Windows x64 (CUDA 13) - CUDA 13.4 DLLs
- Windows arm64 (CUDA 13) - CUDA 13.4 DLLs
- Windows x64 (Vulkan)
- Windows arm64 (Vulkan)
- Windows x64 (OpenVINO)
- Windows x64 (SYCL)
- Windows x64 (ROCm 10.0)
openEuler:
- DISABLED
- openEuler x86 (310p)
- openEuler x86 (910b, ACL Graph)
- openEuler aarch64 (310p)
- openEuler aarch64 (910b, ACL Graph)
UI:
- UI

hexagon: add pool op support (#29995)
- hexagon: add pool_2d support
- hexagon: add pool_1d support
- hex-pool: dma changes
- hex-pool: Optimize HTP pooling boundaries and DMA pipelining
- hex-pool: code cleanup and correctness fixes
- hex-pool: re-write the DMA pipeline
- hex-pool: pool chunking support
- hex-pool: remove/vectorize all scalar paths
- hex-pool: simplify chunk solver (no need for a loop)
- hex-pool: remove redundant checks
Co-authored-by: Max Krasnyansky maxk@qti.qualcomm.com
Website:
- https://llama.app
Attestations:
- https://github.com/ggml-org/llama.cpp/attestations/52990527
macOS/iOS:
- macOS Apple Silicon (arm64)
- macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED
- macOS Intel (x64)
- iOS XCFramework
Linux:
- Ubuntu x64 (CPU)
- Ubuntu arm64 (CPU)
- Ubuntu s390x (CPU)
- Ubuntu x64 (Vulkan)
- Ubuntu arm64 (Vulkan)
- Ubuntu x64 (CUDA 12) - CUDA 12.8 libraries
- Ubuntu x64 (CUDA 13) - CUDA 13.4 libraries
- Ubuntu arm64 (CUDA 13) - CUDA 13.4 libraries
- Ubuntu x64 (ROCm 10.0)
- Ubuntu x64 (OpenVINO)
- Ubuntu x64 (SYCL FP32)
- Ubuntu x64 (SYCL FP16)
- Linux arm64 (Snapdragon: CPU, Adreno GPU, Hexagon NPU) - setup guide
Android:
- Android arm64 (CPU)
- Android arm64 (Snapdragon: CPU, Adreno GPU, Hexagon NPU) - setup guide
Windows:
- Windows x64 (CPU)
- Windows arm64 (CPU)
- Windows arm64 (OpenCL Adreno)
- Windows x64 (CUDA 12) - CUDA 12.4 DLLs
- Windows x64 (CUDA 13) - CUDA 13.4 DLLs
- Windows arm64 (CUDA 13) - CUDA 13.4 DLLs
- Windows x64 (Vulkan)
- Windows arm64 (Vulkan)
- Windows x64 (OpenVINO)
- Windows x64 (SYCL)
- Windows x64 (ROCm 10.0)
openEuler:
- DISABLED
- openEuler x86 (310p)
- openEuler x86 (910b, ACL Graph)
- openEuler aarch64 (310p)
- openEuler aarch64 (910b, ACL Graph)
UI:
- UI

webgpu: add MMVQ support for Q1_0/Q5_0/Q5_1/Q3_K/Q5_K/Q6_K/MXFP4 (#29483)
- add supports for q1/q5/q3_k/q5_k/q6_k/mxfp4 of mmvq path
- Add K_QUANTS_HANDLING macro to q1_0 of mmvq path
Website:
- https://llama.app
Attestations:
- https://github.com/ggml-org/llama.cpp/attestations/52742465
macOS/iOS:
- macOS Apple Silicon (arm64)
- macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED
- macOS Intel (x64)
- iOS XCFramework
Linux:
- Ubuntu x64 (CPU)
- Ubuntu arm64 (CPU)
- Ubuntu s390x (CPU)
- Ubuntu x64 (Vulkan)
- Ubuntu arm64 (Vulkan)
- Ubuntu x64 (CUDA 12) - CUDA 12.8 libraries
- Ubuntu x64 (CUDA 13) - CUDA 13.4 libraries
- Ubuntu arm64 (CUDA 13) - CUDA 13.4 libraries
- Ubuntu x64 (ROCm 10.0)
- Ubuntu x64 (OpenVINO)
- Ubuntu x64 (SYCL FP32)
- Ubuntu x64 (SYCL FP16)
- Linux arm64 (Snapdragon: CPU, Adreno GPU, Hexagon NPU) - setup guide
Android:
- Android arm64 (CPU)
- Android arm64 (Snapdragon: CPU, Adreno GPU, Hexagon NPU) - setup guide
Windows:
- Windows x64 (CPU)
- Windows arm64 (CPU)
- Windows arm64 (OpenCL Adreno)
- Windows x64 (CUDA 12) - CUDA 12.4 DLLs
- Windows x64 (CUDA 13) - CUDA 13.4 DLLs
- Windows arm64 (CUDA 13) - CUDA 13.4 DLLs
- Windows x64 (Vulkan)
- Windows arm64 (Vulkan)
- Windows x64 (OpenVINO)
- Windows x64 (SYCL)
- Windows x64 (ROCm 10.0)
openEuler:
- DISABLED
- openEuler x86 (310p)
- openEuler x86 (910b, ACL Graph)
- openEuler aarch64 (310p)
- openEuler aarch64 (910b, ACL Graph)
UI:
- UI

webgpu: add f16 support to fill/set_rows (#29897)
Website:
- https://llama.app
Attestations:
- https://github.com/ggml-org/llama.cpp/attestations/52497832
macOS/iOS:
- macOS Apple Silicon (arm64)
- macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED
- macOS Intel (x64)
- iOS XCFramework
Linux:
- Ubuntu x64 (CPU)
- Ubuntu arm64 (CPU)
- Ubuntu s390x (CPU)
- Ubuntu x64 (Vulkan)
- Ubuntu arm64 (Vulkan)
- Ubuntu x64 (CUDA 12) - CUDA 12.8 libraries
- Ubuntu x64 (CUDA 13) - CUDA 13.4 libraries
- Ubuntu arm64 (CUDA 13) - CUDA 13.4 libraries
- Ubuntu x64 (ROCm 10.0)
- Ubuntu x64 (OpenVINO)
- Ubuntu x64 (SYCL FP32)
- Ubuntu x64 (SYCL FP16)
- Linux arm64 (Snapdragon: CPU, Adreno GPU, Hexagon NPU) - setup guide
Android:
- Android arm64 (CPU)
- Android arm64 (Snapdragon: CPU, Adreno GPU, Hexagon NPU) - setup guide
Windows:
- Windows x64 (CPU)
- Windows arm64 (CPU)
- Windows arm64 (OpenCL Adreno)
- Windows x64 (CUDA 12) - CUDA 12.4 DLLs
- Windows x64 (CUDA 13) - CUDA 13.4 DLLs
- Windows arm64 (CUDA 13) - CUDA 13.4 DLLs
- Windows x64 (Vulkan)
- Windows x64 (OpenVINO)
- Windows x64 (SYCL)
- Windows x64 (ROCm 10.0)
openEuler:
- DISABLED
- openEuler x86 (310p)
- openEuler x86 (910b, ACL Graph)
- openEuler aarch64 (310p)
- openEuler aarch64 (910b, ACL Graph)
UI:
- UI

hexagon: find software divide calls using binary inspection tool (#29449)
- hex-scripts: fix table alignment
- hex-scripts: find sw div calls using binary inspection tool
Website:
- https://llama.app
Attestations:
- https://github.com/ggml-org/llama.cpp/attestations/50359675
macOS/iOS:
- macOS Apple Silicon (arm64)
- macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED
- macOS Intel (x64)
- iOS XCFramework
Linux:
- Ubuntu x64 (CPU)
- Ubuntu arm64 (CPU)
- Ubuntu s390x (CPU)
- Ubuntu x64 (Vulkan)
- Ubuntu arm64 (Vulkan)
- Ubuntu x64 (CUDA 12) - CUDA 12.8 libraries
- Ubuntu x64 (CUDA 13) - CUDA 13.4 libraries
- Ubuntu arm64 (CUDA 13) - CUDA 13.4 libraries
- Ubuntu x64 (ROCm 10.0)
- Ubuntu x64 (OpenVINO)
- Ubuntu x64 (SYCL FP32)
- Ubuntu x64 (SYCL FP16)
- Linux arm64 (Snapdragon: CPU, Adreno GPU, Hexagon NPU) - setup guide
Android:
- Android arm64 (CPU)
- Android arm64 (Snapdragon: CPU, Adreno GPU, Hexagon NPU) - setup guide
Windows:
- Windows x64 (CPU)
- Windows arm64 (CPU)
- Windows arm64 (OpenCL Adreno)
- Windows x64 (CUDA 12) - CUDA 12.4 DLLs
- Windows x64 (CUDA 13) - CUDA 13.4 DLLs
- Windows arm64 (CUDA 13) - CUDA 13.4 DLLs
- Windows x64 (Vulkan)
- Windows x64 (OpenVINO)
- Windows x64 (SYCL)
- Windows x64 (ROCm 10.0)
openEuler:
- DISABLED
- openEuler x86 (310p)
- openEuler x86 (910b, ACL Graph)
- openEuler aarch64 (310p)
- openEuler aarch64 (910b, ACL Graph)
UI:
- UI

hexagon: add q5_k quant type support (#29123)
Website:
- https://llama.app
Attestations:
- https://github.com/ggml-org/llama.cpp/attestations/50064037
macOS/iOS:
- macOS Apple Silicon (arm64)
- macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED
- macOS Intel (x64)
- iOS XCFramework
Linux:
- Ubuntu x64 (CPU)
- Ubuntu arm64 (CPU)
- Ubuntu s390x (CPU)
- Ubuntu x64 (Vulkan)
- Ubuntu arm64 (Vulkan)
- Ubuntu x64 (CUDA 12) - CUDA 12.8 libraries
- Ubuntu x64 (CUDA 13) - CUDA 13.4 libraries
- Ubuntu arm64 (CUDA 13) - CUDA 13.4 libraries
- Ubuntu x64 (ROCm 10.0)
- Ubuntu x64 (OpenVINO)
- Ubuntu x64 (SYCL FP32)
- Ubuntu x64 (SYCL FP16)
- Linux arm64 (Snapdragon: CPU, Adreno GPU, Hexagon NPU) - setup guide
Android:
- Android arm64 (CPU)
- Android arm64 (Snapdragon: CPU, Adreno GPU, Hexagon NPU) - setup guide
Windows:
- Windows x64 (CPU)
- Windows arm64 (CPU)
- Windows arm64 (OpenCL Adreno)
- Windows x64 (CUDA 12) - CUDA 12.4 DLLs
- Windows x64 (CUDA 13) - CUDA 13.4 DLLs
- Windows arm64 (CUDA 13) - CUDA 13.4 DLLs
- Windows x64 (Vulkan)
- Windows x64 (OpenVINO)
- Windows x64 (SYCL)
- Windows x64 (ROCm 10.0)
openEuler:
- DISABLED
- openEuler x86 (310p)
- openEuler x86 (910b, ACL Graph)
- openEuler aarch64 (310p)
- openEuler aarch64 (910b, ACL Graph)
UI:
- UI

tests: add -b/--backend option to test-llama-archs for testing a specific backend (#27372)
- tests: add backend option to test-llama-archs
- Update tests/test-llama-archs.cpp
Co-authored-by: Johannes Gäßler johannesg@5d6.de
- remove extra space
Co-authored-by: Johannes Gäßler johannesg@5d6.de
Website:
- https://llama.app
Attestations:
- https://github.com/ggml-org/llama.cpp/attestations/49661383
macOS/iOS:
- macOS Apple Silicon (arm64)
- macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED
- macOS Intel (x64)
- iOS XCFramework
Linux:
- Ubuntu x64 (CPU)
- Ubuntu arm64 (CPU)
- Ubuntu s390x (CPU)
- Ubuntu x64 (Vulkan)
- Ubuntu arm64 (Vulkan)
- Ubuntu x64 (CUDA 12) - CUDA 12.8 libraries
- Ubuntu x64 (CUDA 13) - CUDA 13.4 libraries
- Ubuntu arm64 (CUDA 13) - CUDA 13.4 libraries
- Ubuntu x64 (ROCm 10.0)
- Ubuntu x64 (OpenVINO)
- Ubuntu x64 (SYCL FP32)
- Ubuntu x64 (SYCL FP16)
- Linux arm64 (Snapdragon: CPU, Adreno GPU, Hexagon NPU) - setup guide
Android:
- Android arm64 (CPU)
- Android arm64 (Snapdragon: CPU, Adreno GPU, Hexagon NPU) - setup guide
Windows:
- Windows x64 (CPU)
- Windows arm64 (CPU)
- Windows arm64 (OpenCL Adreno)
- Windows x64 (CUDA 12) - CUDA 12.4 DLLs
- Windows x64 (CUDA 13) - CUDA 13.4 DLLs
- Windows arm64 (CUDA 13) - CUDA 13.4 DLLs
- Windows x64 (Vulkan)
- Windows x64 (OpenVINO)
- Windows x64 (SYCL)
- Windows x64 (ROCm 10.0)
openEuler:
- DISABLED
- openEuler x86 (310p)
- openEuler x86 (910b, ACL Graph)
- openEuler aarch64 (310p)
- openEuler aarch64 (910b, ACL Graph)
UI:
- UI

hex-dma: introduce direct-mapped DMA cache that is better suited for HVX FA mask handling (#29282)
Website:
- https://llama.app
Attestations:
- https://github.com/ggml-org/llama.cpp/attestations/49404271
macOS/iOS:
- macOS Apple Silicon (arm64)
- macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED
- macOS Intel (x64)
- iOS XCFramework
Linux:
- Ubuntu x64 (CPU)
- Ubuntu arm64 (CPU)
- Ubuntu s390x (CPU)
- Ubuntu x64 (Vulkan)
- Ubuntu arm64 (Vulkan)
- Ubuntu x64 (CUDA 12) - CUDA 12.8 libraries
- Ubuntu x64 (CUDA 13) - CUDA 13.4 libraries
- Ubuntu arm64 (CUDA 13) - CUDA 13.4 libraries
- Ubuntu x64 (ROCm 10.0)
- Ubuntu x64 (OpenVINO)
- Ubuntu x64 (SYCL FP32)
- Ubuntu x64 (SYCL FP16)
- Linux arm64 (Snapdragon: CPU, Adreno GPU, Hexagon NPU) - setup guide
Android:
- Android arm64 (CPU)
- Android arm64 (Snapdragon: CPU, Adreno GPU, Hexagon NPU) - setup guide
Windows:
- Windows x64 (CPU)
- Windows arm64 (CPU)
- Windows arm64 (OpenCL Adreno)
- Windows x64 (CUDA 12) - CUDA 12.4 DLLs
- Windows x64 (CUDA 13) - CUDA 13.4 DLLs
- Windows arm64 (CUDA 13) - CUDA 13.4 DLLs
- Windows x64 (Vulkan)
- Windows x64 (OpenVINO)
- Windows x64 (SYCL)
- Windows x64 (ROCm 10.0)
openEuler:
- DISABLED
- openEuler x86 (310p)
- openEuler x86 (910b, ACL Graph)
- openEuler aarch64 (310p)
- openEuler aarch64 (910b, ACL Graph)
UI:
- UI

hexagon: new HMX-optimized GATED_DELTA_NET (#29199)
- hex-gdn: start putting together HMX support for GDN
- hex-gdn: working hmx but not-pipelined and slow for now
- hex-gdn: re-write vtcm layout handling and prep for pipelining
- hex-gdn: starting to pipeline hmx and dmas
- hex-gdn: add hvx threading for most pipeline stages
- hex-gdb: add detailed trace events
- hex-gdn: vectorize expfs and use aligned hvx reads/writes
- hex-gnd: vectorize the rest of expf
- hex-gdn: optimize tail processing (pad partial chunks)
- hex-gdb: avoid float up/down casts in hot loops
- hex-fa: remove float up/down casts from inner loops
- hex-gdn: do exp() in f16 to improve HVX utilization
- hex-gdn: optimize tiler
- hex-hmx: bump hmx-queue to 128 and dispatch all GDN gemms at once
- hex-gdn: further pipeline improvements
- hex-gdn: optimize gdn prep stage
- hex-gdn: yet more tweaks to optimize GND_SOLVE task and pipeline
- hex-gdn: improve accuracy and optmize gdn-prep further
- hex-gdn: fix rebase conflict
- hex-bufs: revert max_bufsize enforcement, it is enough to just enforce max_vmem
- hex-scripts: improved inspect script to avoid false alarms in reg spill detector
- hex-fa: improve inline softmax with in-reg VKQ32 accum
- hex-fa: minor improvement for dma pipeline in hvx kernel
- hex-fa: reduce ddr reads by 20-30% during token gen
- hex-gdn: proper alignment for hvx vtcm spads
Website:
- https://llama.app
Attestations:
- https://github.com/ggml-org/llama.cpp/attestations/49097080
macOS/iOS:
- macOS Apple Silicon (arm64)
- macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED
- macOS Intel (x64)
- iOS XCFramework
Linux:
- Ubuntu x64 (CPU)
- Ubuntu arm64 (CPU)
- Ubuntu s390x (CPU)
- Ubuntu x64 (Vulkan)
- Ubuntu arm64 (Vulkan)
- Ubuntu x64 (CUDA 12) - CUDA 12.8 libraries
- Ubuntu x64 (CUDA 13) - CUDA 13.4 libraries
- Ubuntu arm64 (CUDA 13) - CUDA 13.4 libraries
- Ubuntu x64 (ROCm 10.0)
- Ubuntu x64 (OpenVINO)
- Ubuntu x64 (SYCL FP32)
- Ubuntu x64 (SYCL FP16)
Android:
- Android arm64 (CPU)
Windows:
- Windows x64 (CPU)
- Windows arm64 (CPU)
- Windows arm64 (OpenCL Adreno)
- Windows x64 (CUDA 12) - CUDA 12.4 DLLs
- Windows x64 (CUDA 13) - CUDA 13.4 DLLs
- Windows arm64 (CUDA 13) - CUDA 13.4 DLLs
- Windows x64 (Vulkan)
- Windows x64 (OpenVINO)
- Windows x64 (SYCL)
- Windows x64 (ROCm 10.0)
openEuler:
- DISABLED
- openEuler x86 (310p)
- openEuler x86 (910b, ACL Graph)
- openEuler aarch64 (310p)
- openEuler aarch64 (910b, ACL Graph)
UI:
- UI

chat : add dedicated Ling 3.0 (Bailing V3) parser (#28682)
- chat: add dedicated Ling 3.0 (Bailing V3) parser
Ling 3.0 Flash templates pre-open the think block in the generation
prompt, so the model never emits an opening , and a tool call can
arrive before any . The generated autoparser terminated reasoning
only at the close tag, which classified such tool calls entirely as
reasoning_content: clients received content="" with no tool_calls and
agent loops died as reasoning-only turns.
Adds a specialized parser that terminates reasoning at the think close
tag or at a <tool_call> start, mirroring the hand-written Qwen3-Coder and
Kimi K3 parsers and the reference vLLM/SGLang Ling3 parser (which treats
<tool_call> as an implicit reasoning terminator). Detection is gated on
the ... section markers, unique to this family among the
tagged-argument templates.
Adds the Ling 3.0 Flash chat template and tests covering the
unclosed-think tool call (full parse and streaming), healthy closed-think
paths, trailing prose, parallel calls, marker-like strings in argument
values, string-union and non-string argument types, and
reasoning_format=none.
Assisted-by: Kimi Code
- tests : move Ling 3.0 test
Co-authored-by: aetherbird aetherbird@users.noreply.github.com
Co-authored-by: Alde Rojas hello@alde.dev
Website:
- https://llama.app
Attestations:
- https://github.com/ggml-org/llama.cpp/attestations/48695438
macOS/iOS:
- macOS Apple Silicon (arm64)
- macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED
- macOS Intel (x64)
- iOS XCFramework
Linux:
- Ubuntu x64 (CPU)
- Ubuntu arm64 (CPU)
- Ubuntu s390x (CPU)
- Ubuntu x64 (Vulkan)
- Ubuntu arm64 (Vulkan)
- Ubuntu x64 (CUDA 12) - CUDA 12.8 libraries
- Ubuntu x64 (CUDA 13) - CUDA 13.3 libraries
- Ubuntu arm64 (CUDA 13) - CUDA 13.3 libraries
- Ubuntu x64 (ROCm 10.0)
- Ubuntu x64 (OpenVINO)
- Ubuntu x64 (SYCL FP32)
- Ubuntu x64 (SYCL FP16)
Android:
- Android arm64 (CPU)
Windows:
- Windows x64 (CPU)
- Windows arm64 (CPU)
- Windows arm64 (OpenCL Adreno)
- Windows x64 (CUDA 12) - CUDA 12.4 DLLs
- Windows x64 (CUDA 13) - CUDA 13.4 DLLs
- Windows arm64 (CUDA 13) - CUDA 13.4 DLLs
- Windows x64 (Vulkan)
- Windows x64 (OpenVINO)
- Windows x64 (SYCL)
- Windows x64 (ROCm 10.0)
openEuler:
- DISABLED
- openEuler x86 (310p)
- openEuler x86 (910b, ACL Graph)
- openEuler aarch64 (310p)
- openEuler aarch64 (910b, ACL Graph)
UI:
- UI

opencl: add support for bin kernel flash_attn_f32_f16_bin (#29046)
- opencl: add flash_attn_f32_f16_bin
- opencl: guarded prefill fa
Website:
- https://llama.app
Attestations:
- https://github.com/ggml-org/llama.cpp/attestations/48577094
macOS/iOS:
- macOS Apple Silicon (arm64)
- macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED
- macOS Intel (x64)
- iOS XCFramework
Linux:
- Ubuntu x64 (CPU)
- Ubuntu arm64 (CPU)
- Ubuntu s390x (CPU)
- Ubuntu x64 (Vulkan)
- Ubuntu arm64 (Vulkan)
- Ubuntu x64 (CUDA 12) - CUDA 12.8 libraries
- Ubuntu x64 (CUDA 13) - CUDA 13.3 libraries
- Ubuntu arm64 (CUDA 13) - CUDA 13.3 libraries
- Ubuntu x64 (ROCm 10.0)
- Ubuntu x64 (OpenVINO)
- Ubuntu x64 (SYCL FP32)
- Ubuntu x64 (SYCL FP16)
Android:
- Android arm64 (CPU)
Windows:
- Windows x64 (CPU)
- Windows arm64 (CPU)
- Windows arm64 (OpenCL Adreno)
- Windows x64 (CUDA 12) - CUDA 12.4 DLLs
- Windows x64 (CUDA 13) - CUDA 13.4 DLLs
- Windows arm64 (CUDA 13) - CUDA 13.4 DLLs
- Windows x64 (Vulkan)
- Windows x64 (OpenVINO)
- Windows x64 (SYCL)
- Windows x64 (ROCm 10.0)
openEuler:
- DISABLED
- openEuler x86 (310p)
- openEuler x86 (910b, ACL Graph)
- openEuler aarch64 (310p)
- openEuler aarch64 (910b, ACL Graph)
UI:
- UI

model : skip gate_up_exps if TENSOR_SKIP is set (#29014)
required for qwen35moe if MTP tensors are fused but not loaded
Website:
- https://llama.app
Attestations:
- https://github.com/ggml-org/llama.cpp/attestations/48194938
macOS/iOS:
- macOS Apple Silicon (arm64)
- macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED
- macOS Intel (x64)
- iOS XCFramework
Linux:
- Ubuntu x64 (CPU)
- Ubuntu arm64 (CPU)
- Ubuntu s390x (CPU)
- Ubuntu x64 (Vulkan)
- Ubuntu arm64 (Vulkan)
- Ubuntu x64 (CUDA 12) - CUDA 12.8 libraries
- Ubuntu x64 (CUDA 13) - CUDA 13.3 libraries
- Ubuntu arm64 (CUDA 13) - CUDA 13.3 libraries
- Ubuntu x64 (ROCm 10.0)
- Ubuntu x64 (OpenVINO)
- Ubuntu x64 (SYCL FP32)
- Ubuntu x64 (SYCL FP16)
Android:
- Android arm64 (CPU)
Windows:
- Windows x64 (CPU)
- Windows arm64 (CPU)
- Windows arm64 (OpenCL Adreno)
- Windows x64 (CUDA 12) - CUDA 12.4 DLLs
- Windows x64 (CUDA 13) - CUDA 13.4 DLLs
- Windows arm64 (CUDA 13) - CUDA 13.4 DLLs
- Windows x64 (Vulkan)
- Windows x64 (OpenVINO)
- Windows x64 (SYCL)
- Windows x64 (ROCm 10.0)
openEuler:
- DISABLED
- openEuler x86 (310p)
- openEuler x86 (910b, ACL Graph)
- openEuler aarch64 (310p)
- openEuler aarch64 (910b, ACL Graph)
UI:
- UI

opencl: fix various warnings (#28984)
- opencl: fix warnings
- opencl: fix warnings for non adreno
Website:
- https://llama.app
Attestations:
- https://github.com/ggml-org/llama.cpp/attestations/48132480
macOS/iOS:
- macOS Apple Silicon (arm64)
- macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED
- macOS Intel (x64)
- iOS XCFramework
Linux:
- Ubuntu x64 (CPU)
- Ubuntu arm64 (CPU)
- Ubuntu s390x (CPU)
- Ubuntu x64 (Vulkan)
- Ubuntu arm64 (Vulkan)
- Ubuntu x64 (CUDA 12) - CUDA 12.8 libraries
- Ubuntu x64 (CUDA 13) - CUDA 13.3 libraries
- Ubuntu arm64 (CUDA 13) - CUDA 13.3 libraries
- Ubuntu x64 (ROCm 10.0)
- Ubuntu x64 (OpenVINO)
- Ubuntu x64 (SYCL FP32)
- Ubuntu x64 (SYCL FP16)
Android:
- Android arm64 (CPU)
Windows:
- Windows x64 (CPU)
- Windows arm64 (CPU)
- Windows arm64 (OpenCL Adreno)
- Windows x64 (CUDA 12) - CUDA 12.4 DLLs
- Windows x64 (CUDA 13) - CUDA 13.4 DLLs
- Windows arm64 (CUDA 13) - CUDA 13.4 DLLs
- Windows x64 (Vulkan)
- Windows x64 (OpenVINO)
- Windows x64 (SYCL)
- Windows x64 (ROCm 10.0)
openEuler:
- DISABLED
- openEuler x86 (310p)
- openEuler x86 (910b, ACL Graph)
- openEuler aarch64 (310p)
- openEuler aarch64 (910b, ACL Graph)
UI:
- UI

hexagon: add back missing contiguous fast-path and hvx_copy_uu for each run (#28886)
Website:
- https://llama.app
Attestations:
- https://github.com/ggml-org/llama.cpp/attestations/47775478
macOS/iOS:
- macOS Apple Silicon (arm64)
- macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED
- macOS Intel (x64)
- iOS XCFramework
Linux:
- Ubuntu x64 (CPU)
- Ubuntu arm64 (CPU)
- Ubuntu s390x (CPU)
- Ubuntu x64 (Vulkan)
- Ubuntu arm64 (Vulkan)
- Ubuntu x64 (CUDA 12) - CUDA 12.8 libraries
- Ubuntu x64 (CUDA 13) - CUDA 13.3 libraries
- Ubuntu arm64 (CUDA 13) - CUDA 13.3 libraries
- Ubuntu x64 (ROCm 10.0)
- Ubuntu x64 (OpenVINO)
- Ubuntu x64 (SYCL FP32)
- Ubuntu x64 (SYCL FP16)
Android:
- Android arm64 (CPU)
Windows:
- Windows x64 (CPU)
- Windows arm64 (CPU)
- Windows arm64 (OpenCL Adreno)
- Windows x64 (CUDA 12) - CUDA 12.4 DLLs
- Windows x64 (CUDA 13) - CUDA 13.4 DLLs
- Windows arm64 (CUDA 13) - CUDA 13.4 DLLs
- Windows x64 (Vulkan)
- Windows x64 (OpenVINO)
- Windows x64 (SYCL)
- Windows x64 (ROCm 10.0)
openEuler:
- DISABLED
- openEuler x86 (310p)
- openEuler x86 (910b, ACL Graph)
- openEuler aarch64 (310p)
- openEuler aarch64 (910b, ACL Graph)
UI:
- UI

HIP: fattn-mma: use fp32 accumulation on MFMA devices (#28576)
use fp32 accumulators in fattn-mma on CDNA
Website:
- https://llama.app
Attestations:
- https://github.com/ggml-org/llama.cpp/attestations/47450174
macOS/iOS:
- macOS Apple Silicon (arm64)
- macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED
- macOS Intel (x64)
- iOS XCFramework
Linux:
- Ubuntu x64 (CPU)
- Ubuntu arm64 (CPU)
- Ubuntu s390x (CPU)
- Ubuntu x64 (Vulkan)
- Ubuntu arm64 (Vulkan)
- Ubuntu x64 (CUDA 12) - CUDA 12.8 libraries
- Ubuntu x64 (CUDA 13) - CUDA 13.3 libraries
- Ubuntu arm64 (CUDA 13) - CUDA 13.3 libraries
- Ubuntu x64 (ROCm 10.0)
- Ubuntu x64 (OpenVINO)
- Ubuntu x64 (SYCL FP32)
- Ubuntu x64 (SYCL FP16)
Android:
- Android arm64 (CPU)
Windows:
- Windows x64 (CPU)
- Windows arm64 (CPU)
- Windows arm64 (OpenCL Adreno)
- Windows x64 (CUDA 12) - CUDA 12.4 DLLs
- Windows x64 (CUDA 13) - CUDA 13.3 DLLs
- Windows arm64 (CUDA 13) - CUDA 13.4 DLLs
- Windows x64 (Vulkan)
- Windows x64 (OpenVINO)
- Windows x64 (SYCL)
- Windows x64 (ROCm 10.0)
openEuler:
- DISABLED
- openEuler x86 (310p)
- openEuler x86 (910b, ACL Graph)
- openEuler aarch64 (310p)
- openEuler aarch64 (910b, ACL Graph)
UI:
- UI

common : move llama_n_rs_seq to before llama_decode (#28749)
This commit moves the llama_n_rs_seq function call to before the
llama_decode call and returns directly if the check is true, removing
the setting of res and the goto statement.
The motivation for this change is to avoid the llama_decode call if it
is not needed.
Website:
- https://llama.app
Attestations:
- https://github.com/ggml-org/llama.cpp/attestations/47247883
macOS/iOS:
- macOS Apple Silicon (arm64)
- macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED
- macOS Intel (x64)
- iOS XCFramework
Linux:
- Ubuntu x64 (CPU)
- Ubuntu arm64 (CPU)
- Ubuntu s390x (CPU)
- Ubuntu x64 (Vulkan)
- Ubuntu arm64 (Vulkan)
- Ubuntu x64 (ROCm 10.0)
- Ubuntu x64 (OpenVINO)
- Ubuntu x64 (SYCL FP32)
- Ubuntu x64 (SYCL FP16)
Android:
- Android arm64 (CPU)
Windows:
- Windows x64 (CPU)
- Windows arm64 (CPU)
- Windows arm64 (OpenCL Adreno)
- Windows x64 (CUDA 12) - CUDA 12.4 DLLs
- Windows x64 (CUDA 13) - CUDA 13.3 DLLs
- Windows arm64 (CUDA 13) - CUDA 13.4 DLLs
- Windows x64 (Vulkan)
- Windows x64 (OpenVINO)
- Windows x64 (SYCL)
- Windows x64 (ROCm 10.0)
openEuler:
- DISABLED
- openEuler x86 (310p)
- openEuler x86 (910b, ACL Graph)
- openEuler aarch64 (310p)
- openEuler aarch64 (910b, ACL Graph)
UI:
- UI

ggml-webgpu: Update to a recent version of Dawn (#28683)
- ggml-webgpu: Update to a recent version of Dawn
- No module scanning
- Accept review suggestion to update comment
Co-authored-by: Masashi Yoshimura yoshimura.masashi.frbs@gmail.com
Co-authored-by: Masashi Yoshimura yoshimura.masashi.frbs@gmail.com
Website:
- https://llama.app
Attestations:
- https://github.com/ggml-org/llama.cpp/attestations/47005667
macOS/iOS:
- macOS Apple Silicon (arm64)
- macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED
- macOS Intel (x64)
- iOS XCFramework
Linux:
- Ubuntu x64 (CPU)
- Ubuntu arm64 (CPU)
- Ubuntu s390x (CPU)
- Ubuntu x64 (Vulkan)
- Ubuntu arm64 (Vulkan)
- Ubuntu x64 (ROCm 10.0)
- Ubuntu x64 (OpenVINO)
- Ubuntu x64 (SYCL FP32)
- Ubuntu x64 (SYCL FP16)
Android:
- Android arm64 (CPU)
Windows:
- Windows x64 (CPU)
- Windows arm64 (CPU)
- Windows arm64 (OpenCL Adreno)
- Windows x64 (CUDA 12) - CUDA 12.4 DLLs
- Windows x64 (CUDA 13) - CUDA 13.3 DLLs
- Windows arm64 (CUDA 13) - CUDA 13.4 DLLs
- Windows x64 (Vulkan)
- Windows x64 (OpenVINO)
- Windows x64 (SYCL)
- Windows x64 (ROCm 10.0)
openEuler:
- DISABLED
- openEuler x86 (310p)
- openEuler x86 (910b, ACL Graph)
- openEuler aarch64 (310p)
- openEuler aarch64 (910b, ACL Graph)
UI:
- UI

vulkan: use CPU writes in ggml_backend_vk_cpy_tensor_async if the context is idle (#28618)
Website:
- https://llama.app
Attestations:
- https://github.com/ggml-org/llama.cpp/attestations/46709648
macOS/iOS:
- macOS Apple Silicon (arm64)
- macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED
- macOS Intel (x64)
- iOS XCFramework
Linux:
- Ubuntu x64 (CPU)
- Ubuntu arm64 (CPU)
- Ubuntu s390x (CPU)
- Ubuntu x64 (Vulkan)
- Ubuntu arm64 (Vulkan)
- Ubuntu x64 (ROCm 10.0)
- Ubuntu x64 (OpenVINO)
- Ubuntu x64 (SYCL FP32)
- Ubuntu x64 (SYCL FP16)
Android:
- Android arm64 (CPU)
Windows:
- Windows x64 (CPU)
- Windows arm64 (CPU)
- Windows arm64 (OpenCL Adreno)
- Windows x64 (CUDA 12) - CUDA 12.4 DLLs
- Windows x64 (CUDA 13) - CUDA 13.3 DLLs
- Windows arm64 (CUDA 13) - CUDA 13.4 DLLs
- Windows x64 (Vulkan)
- Windows x64 (OpenVINO)
- Windows x64 (SYCL)
- Windows x64 (ROCm 10.0)
openEuler:
- DISABLED
- openEuler x86 (310p)
- openEuler x86 (910b, ACL Graph)
- openEuler aarch64 (310p)
- openEuler aarch64 (910b, ACL Graph)
UI:
- UI

vulkan: use spec constant for matrix matrix multiplication A-type (#25773)
- vulkan: use spec constant for mul mat type_a
vulkan: use map for mul_mm shapes
cleanup
fix indentation
fix cm2 and shmem init
fix cm2 spec constants
fix cm2 bindings
consolidate shmem tables and reduce size by type spec constant
fix compiler warning
fix missing Q2_0 type
fix unused warning when integer dot glslc support is missing
use minimal shmem size 8 instead of 1 to workaround cm2 compiler bug
fix missing Q2_0 type in cm2 matmul
fix types
- remove LUT quants from unified shader
- clean up
- restore coopmat2 q4_k/q5_k optimization
- split out q4_k/q5_k cm2 shader to fix Ampere regression
- revert iq shmem table renames
- simplify cm2 code with single uint8_t buffer
- fix fp4 extension use switch being overwritten by generic shader
- clean up
- adapt TQ1_0 changes
- adapt #27471 f16 Intel tuning changes
Website:
- https://llama.app
Attestations:
- https://github.com/ggml-org/llama.cpp/attestations/46324023
macOS/iOS:
- macOS Apple Silicon (arm64)
- macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED
- macOS Intel (x64)
- iOS XCFramework
Linux:
- Ubuntu x64 (CPU)
- Ubuntu arm64 (CPU)
- Ubuntu s390x (CPU)
- Ubuntu x64 (Vulkan)
- Ubuntu arm64 (Vulkan)
- Ubuntu x64 (ROCm 10.0)
- Ubuntu x64 (OpenVINO)
- Ubuntu x64 (SYCL FP32)
- Ubuntu x64 (SYCL FP16)
Android:
- Android arm64 (CPU)
Windows:
- Windows x64 (CPU)
- Windows arm64 (CPU)
- Windows arm64 (OpenCL Adreno)
- Windows x64 (CUDA 12) - CUDA 12.4 DLLs
- Windows x64 (CUDA 13) - CUDA 13.3 DLLs
- Windows arm64 (CUDA 13) (preview) - CUDA 13.4 DLLs
- Windows x64 (Vulkan)
- Windows x64 (OpenVINO)
- Windows x64 (SYCL)
- Windows x64 (ROCm 10.0)
openEuler:
- DISABLED
- openEuler x86 (310p)
- openEuler x86 (910b, ACL Graph)
- openEuler aarch64 (310p)
- openEuler aarch64 (910b, ACL Graph)
UI:
- UI

tests : use less threads for data initialization (#28325)
- tests : use 1 thread for data initialization
- cont : scale threads with number of elements
- cont : adjust
Website:
- https://llama.app
Attestations:
- https://github.com/ggml-org/llama.cpp/attestations/46152521
macOS/iOS:
- macOS Apple Silicon (arm64)
- macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED
- macOS Intel (x64)
- iOS XCFramework
Linux:
- Ubuntu x64 (CPU)
- Ubuntu arm64 (CPU)
- Ubuntu s390x (CPU)
- Ubuntu x64 (Vulkan)
- Ubuntu arm64 (Vulkan)
- Ubuntu x64 (ROCm 10.0)
- Ubuntu x64 (OpenVINO)
- Ubuntu x64 (SYCL FP32)
- Ubuntu x64 (SYCL FP16)
Android:
- Android arm64 (CPU)
Windows:
- Windows x64 (CPU)
- Windows arm64 (CPU)
- Windows arm64 (OpenCL Adreno)
- Windows x64 (CUDA 12) - CUDA 12.4 DLLs
- Windows x64 (CUDA 13) - CUDA 13.3 DLLs
- Windows arm64 (CUDA 13) (preview) - CUDA 13.4 DLLs
- Windows x64 (Vulkan)
- Windows x64 (OpenVINO)
- Windows x64 (SYCL)
- Windows x64 (ROCm 10.0)
openEuler:
- DISABLED
- openEuler x86 (310p)
- openEuler x86 (910b, ACL Graph)
- openEuler aarch64 (310p)
- openEuler aarch64 (910b, ACL Graph)
UI:
- UI

model : support Kimi-K3 recurrent-state rollback (#28466)
Website:
- https://llama.app
Attestations:
- https://github.com/ggml-org/llama.cpp/attestations/45866131
macOS/iOS:
- macOS Apple Silicon (arm64)
- macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED
- macOS Intel (x64)
- iOS XCFramework
Linux:
- Ubuntu x64 (CPU)
- Ubuntu arm64 (CPU)
- Ubuntu s390x (CPU)
- Ubuntu x64 (Vulkan)
- Ubuntu arm64 (Vulkan)
- Ubuntu x64 (ROCm 10.0)
- Ubuntu x64 (OpenVINO)
- Ubuntu x64 (SYCL FP32)
- Ubuntu x64 (SYCL FP16)
Android:
- Android arm64 (CPU)
Windows:
- Windows x64 (CPU)
- Windows arm64 (CPU)
- Windows arm64 (OpenCL Adreno)
- Windows x64 (CUDA 12) - CUDA 12.4 DLLs
- Windows x64 (CUDA 13) - CUDA 13.3 DLLs
- Windows arm64 (CUDA 13) (preview) - CUDA 13.4 DLLs
- Windows x64 (Vulkan)
- Windows x64 (OpenVINO)
- Windows x64 (SYCL)
- Windows x64 (ROCm 10.0)
openEuler:
- DISABLED
- openEuler x86 (310p)
- openEuler x86 (910b, ACL Graph)
- openEuler aarch64 (310p)
- openEuler aarch64 (910b, ACL Graph)
UI:
- UI

vulkan: add TQ1_0 support (mm, mat-vec, mat-vec-id, dequant, get_rows) (#27765)
- vulkan: add TQ1_0 support (mm, mat-vec, dequant, get_rows)
- vulkan: pack TQ1_0 powers of 3 into a 32-bit constant
Replaces the constant array with a packed 32-bit value (7 bits per entry,
max 81 < 128) extracted with shift/mask, as suggested in review — avoids a
constant array that may not be kept in registers.
test-backend-ops on gfx1151: tq1_0 MUL_MAT 11/11, MUL_MAT_ID 6/6,
GET_ROWS 4/4, unchanged.
- vulkan: address review - shared TQ1_0 decode helpers, fix standalone dequant shader
Review feedback from jeffbolznv, all points:
- Move the packed-pow3 decode into shared helpers in types.glsl
(tq1_0_byte_of / tq1_0_digit_of / tq1_0_trit) and use them from
dequant_funcs.glsl, mul_mm_funcs.glsl, dequant_funcs_cm2.glsl and
dequant_tq1_0.comp instead of repeating the logic. The cm2 path also
drops its constant array for the packed-constant extraction.
- Translate all remaining comments to English.
- dequant_tq1_0.comp: use dequant_head.glsl. The shader previously declared
its own single-field push constant while the pipeline is created with the
5-field layout, so p.ne read the wrong field - confirmed broken, as
suspected in review.
- Fix wg_denoms for the standalone dequant pipeline: one invocation decodes
4 elements with local_size 256, so a workgroup covers 2564 elements, not
25616. With the old value the dispatcher launched a quarter of the
required workgroups.
Verified by temporarily forcing the dequant + f16 matmul path for TQ1_0
(hack not committed): test-backend-ops MUL_MAT passes through the rewritten
standalone shader, and the standard MUL_MAT / MUL_MAT_ID / GET_ROWS
tq1_0 cases still pass on Vulkan (AMD gfx1151).
- vulkan: address review — English comments, shared tq1_0_trit, trim TQ1_0 test cases
- mul_mat_vec_tq1_0.comp: drop leftover non-English comment and the local
POW3_PACKED constant; all decode sites now call tq1_0_trit() from types.glsl
- types.glsl / dequant_funcs_cm2.glsl: ASCII-only, drop stale reviewer note
- test-backend-ops: remove the oversized MUL_MAT_ID case (432 MiB A tensor,
~172 GFLOP reference); move the two remaining ones next to the other
backend-specific mul_mat_id one-offs and document why they are needed
- metal: decline TQ1_0 for GET_ROWS and mat-mul in supports_op
The new TQ1_0 cases in test-backend-ops exposed that the Metal backend
claimed support for GET_ROWS/MUL_MAT/MUL_MAT_ID with TQ1_0 sources while
having no such kernels (ggml_metal_library_compile_pipeline aborted on the
missing kernel_get_rows_tq1_0). Decline the type so the ops fall back to
the CPU, matching the existing NVFP4 handling on the same lines.
Assisted-by: Claude Fable 5
- vulkan: trim the TQ1_0 comments
Addresses @0cc4m's review: keep only what the code does not already say.
Removed the block-format recaps (the layout is right there in the struct) and
the step-by-step decode walkthrough. Kept the two facts a reader cannot infer:
the 8-bit truncation is part of the format, not an optimisation, and the powers
of 3 are packed into one uint so they do not end up in a constant array that
may miss the registers.
No functional change.
- vulkan: address review — trim comments, fold Metal check, drop unused _v
Per @0cc4m's review:
- dequant_funcs.glsl, dequant_funcs_cm2.glsl: drop the "see types.glsl"
pointers — they apply to every quant and say nothing specific.
- dequant_tq1_0.comp: drop the wg_denoms note. It is a precondition, not
information.
- mul_mm_funcs.glsl: same pointer removed.
- types.glsl: the comment on tq1_0_trit is down to the one fact the code
cannot show — the 8-bit truncation is part of the format, matching the C
reference, not an optimisation.
- dequant_funcs_cm2.glsl: removed dequantFuncTQ1_0_v and its define. You were
right that it is optional: it wrapped four scalar decodes and vectorised
nothing, and mul_mm_cm2.comp already guards the path with
#if defined(dequantFuncA_v) (DATA_A_F32 omits it the same way).
- ggml-metal-devi

metal : fix memory leak in early return (#28399)
Website:
- https://llama.app
Attestations:
- https://github.com/ggml-org/llama.cpp/attestations/45438612
macOS/iOS:
- macOS Apple Silicon (arm64)
- macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED
- macOS Intel (x64)
- iOS XCFramework
Linux:
- Ubuntu x64 (CPU)
- Ubuntu arm64 (CPU)
- Ubuntu s390x (CPU)
- Ubuntu x64 (Vulkan)
- Ubuntu arm64 (Vulkan)
- Ubuntu x64 (ROCm 10.0)
- Ubuntu x64 (OpenVINO)
- Ubuntu x64 (SYCL FP32)
- Ubuntu x64 (SYCL FP16)
Android:
- Android arm64 (CPU)
Windows:
- Windows x64 (CPU)
- Windows arm64 (CPU)
- Windows arm64 (OpenCL Adreno)
- Windows x64 (CUDA 12) - CUDA 12.4 DLLs
- Windows x64 (CUDA 13) - CUDA 13.3 DLLs
- Windows arm64 (CUDA 13) (preview) - CUDA 13.4 DLLs
- Windows x64 (Vulkan)
- Windows x64 (OpenVINO)
- Windows x64 (SYCL)
- Windows x64 (ROCm 10.0)
openEuler:
- DISABLED
- openEuler x86 (310p)
- openEuler x86 (910b, ACL Graph)
- openEuler aarch64 (310p)
- openEuler aarch64 (910b, ACL Graph)
UI:
- UI

metal : add remaining fa-vec tunings for M3 (#28396)
- addition of m3 in fa_vec_tuned_table
- adding q4_0,q4_1,q5_0,q5_1 in ggml-metal-tuning
- Fix formatting in ggml-metal-tuning.cpp
Website:
- https://llama.app
Attestations:
- https://github.com/ggml-org/llama.cpp/attestations/45337508
macOS/iOS:
- macOS Apple Silicon (arm64)
- macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED
- macOS Intel (x64)
- iOS XCFramework
Linux:
- Ubuntu x64 (CPU)
- Ubuntu arm64 (CPU)
- Ubuntu s390x (CPU)
- Ubuntu x64 (Vulkan)
- Ubuntu arm64 (Vulkan)
- Ubuntu x64 (ROCm 10.0)
- Ubuntu x64 (OpenVINO)
- Ubuntu x64 (SYCL FP32)
- Ubuntu x64 (SYCL FP16)
Android:
- Android arm64 (CPU)
Windows:
- Windows x64 (CPU)
- Windows arm64 (CPU)
- Windows arm64 (OpenCL Adreno)
- Windows x64 (CUDA 12) - CUDA 12.4 DLLs
- Windows x64 (CUDA 13) - CUDA 13.3 DLLs
- Windows arm64 (CUDA 13) (preview) - CUDA 13.4 DLLs
- Windows x64 (Vulkan)
- Windows x64 (OpenVINO)
- Windows x64 (SYCL)
- Windows x64 (ROCm 10.0)
openEuler:
- DISABLED
- openEuler x86 (310p)
- openEuler x86 (910b, ACL Graph)
- openEuler aarch64 (310p)
- openEuler aarch64 (910b, ACL Graph)
UI:
- UI

sycl: fuse rms_norm+mul+add and add+add residual chains (#27610)
Fuse RMS_NORM+MUL+ADD and ADD+ADD under GGML_SYCL_ENABLE_FUSION.
ADD+ADD uses the same binbcast indexing and type matrix as standalone
add() (f32, f16, f16/f32, i32, i16, bf16, including broadcast and
non-contiguous). Unsupported combinations fall back to two add() launches.
Website:
- https://llama.app
Attestations:
- https://github.com/ggml-org/llama.cpp/attestations/45161609
macOS/iOS:
- macOS Apple Silicon (arm64)
- macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED
- macOS Intel (x64)
- iOS XCFramework
Linux:
- Ubuntu x64 (CPU)
- Ubuntu arm64 (CPU)
- Ubuntu s390x (CPU)
- Ubuntu x64 (Vulkan)
- Ubuntu arm64 (Vulkan)
- Ubuntu x64 (ROCm 10.0)
- Ubuntu x64 (OpenVINO)
- Ubuntu x64 (SYCL FP32)
- Ubuntu x64 (SYCL FP16)
Android:
- Android arm64 (CPU)
Windows:
- Windows x64 (CPU)
- Windows arm64 (CPU)
- Windows arm64 (OpenCL Adreno)
- Windows x64 (CUDA 12) - CUDA 12.4 DLLs
- Windows x64 (CUDA 13) - CUDA 13.3 DLLs
- Windows arm64 (CUDA 13) (preview) - CUDA 13.4 DLLs
- Windows x64 (Vulkan)
- Windows x64 (OpenVINO)
- Windows x64 (SYCL)
- Windows x64 (ROCm 10.0)
openEuler:
- DISABLED
- openEuler x86 (310p)
- openEuler x86 (910b, ACL Graph)
- openEuler aarch64 (310p)
- openEuler aarch64 (910b, ACL Graph)
UI:
- UI

mtmd: fix idefics3 preproc (#28273)
Website:
- https://llama.app
Attestations:
- https://github.com/ggml-org/llama.cpp/attestations/44875193
macOS/iOS:
- macOS Apple Silicon (arm64)
- macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED
- macOS Intel (x64)
- iOS XCFramework
Linux:
- Ubuntu x64 (CPU)
- Ubuntu arm64 (CPU)
- Ubuntu s390x (CPU)
- Ubuntu x64 (Vulkan)
- Ubuntu arm64 (Vulkan)
- Ubuntu x64 (ROCm 10.0)
- Ubuntu x64 (OpenVINO)
- Ubuntu x64 (SYCL FP32)
- Ubuntu x64 (SYCL FP16)
Android:
- Android arm64 (CPU)
Windows:
- Windows x64 (CPU)
- Windows arm64 (CPU)
- Windows arm64 (OpenCL Adreno)
- Windows x64 (CUDA 12) - CUDA 12.4 DLLs
- Windows x64 (CUDA 13) - CUDA 13.3 DLLs
- Windows arm64 (CUDA 13) (preview) - CUDA 13.4 DLLs
- Windows x64 (Vulkan)
- Windows x64 (OpenVINO)
- Windows x64 (SYCL)
- Windows x64 (ROCm 10.0)
openEuler:
- DISABLED
- openEuler x86 (310p)
- openEuler x86 (910b, ACL Graph)
- openEuler aarch64 (310p)
- openEuler aarch64 (910b, ACL Graph)
UI:
- UI

metal : add metallib build support for xcframework (#28163)
Website:
- https://llama.app
Attestations:
- https://github.com/ggml-org/llama.cpp/attestations/44563342
macOS/iOS:
- macOS Apple Silicon (arm64)
- macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED
- macOS Intel (x64)
- iOS XCFramework
Linux:
- Ubuntu x64 (CPU)
- Ubuntu arm64 (CPU)
- Ubuntu s390x (CPU)
- Ubuntu x64 (Vulkan)
- Ubuntu arm64 (Vulkan)
- Ubuntu x64 (ROCm 7.14)
- Ubuntu x64 (OpenVINO)
- Ubuntu x64 (SYCL FP32)
- Ubuntu x64 (SYCL FP16)
Android:
- Android arm64 (CPU)
Windows:
- Windows x64 (CPU)
- Windows arm64 (CPU)
- Windows arm64 (OpenCL Adreno)
- Windows x64 (CUDA 12) - CUDA 12.4 DLLs
- Windows x64 (CUDA 13) - CUDA 13.3 DLLs
- Windows arm64 (CUDA 13) (preview) - CUDA 13.4 DLLs
- Windows x64 (Vulkan)
- Windows x64 (OpenVINO)
- Windows x64 (SYCL)
- Windows x64 (ROCm 7.14)
openEuler:
- DISABLED
- openEuler x86 (310p)
- openEuler x86 (910b, ACL Graph)
- openEuler aarch64 (310p)
- openEuler aarch64 (910b, ACL Graph)
UI:
- UI

qwen4exp: sum the indexer heads by slices (#28023)
- qwen4exp: sum the indexer heads by slices
The head reduction went through a transpose and a sum_rows over ne[1],
which left sum_rows with ne0 = 4, one block per row for a four element
reduction, and the transpose copied the whole block by token surface
twice on the way in.
The heads are adjacent on ne[1], so each one is a strided view and the
sum is a short chain of adds.
RTX PRO 6000, Qwen3.8-Flash-Next UD-Q4_K_XL, fa on, 55k context, warm
runs on top of #28011:
prompt processing 2170 -> 2366 t/s
Generation is unaffected. The removed work scales with n_blocks by
n_tokens, so the gain grows with context and with ubatch size.
- qwen4exp: drop the redundant cont on the indexer query
rope returns a freshly allocated, contiguous tensor, so the reshape that
feeds the matmul does not need a copy. ggml_reshape_3d asserts
contiguity, so a layout that would need the cont cannot slip through
silently.
Greedy output is unchanged token for token.
Address review from @ggerganov
Website:
- https://llama.app
Attestations:
- https://github.com/ggml-org/llama.cpp/attestations/44321551
macOS/iOS:
- macOS Apple Silicon (arm64)
- macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED
- macOS Intel (x64)
- iOS XCFramework
Linux:
- Ubuntu x64 (CPU)
- Ubuntu arm64 (CPU)
- Ubuntu s390x (CPU)
- Ubuntu x64 (Vulkan)
- Ubuntu arm64 (Vulkan)
- Ubuntu x64 (ROCm 7.14)
- Ubuntu x64 (OpenVINO)
- Ubuntu x64 (SYCL FP32)
- Ubuntu x64 (SYCL FP16)
Android:
- Android arm64 (CPU)
Windows:
- Windows x64 (CPU)
- Windows arm64 (CPU)
- Windows arm64 (OpenCL Adreno)
- Windows x64 (CUDA 12) - CUDA 12.4 DLLs
- Windows x64 (CUDA 13) - CUDA 13.3 DLLs
- Windows arm64 (CUDA 13) (preview) - CUDA 13.4 DLLs
- Windows x64 (Vulkan)
- Windows x64 (OpenVINO)
- Windows x64 (SYCL)
- Windows x64 (ROCm 7.14)
openEuler:
- DISABLED
- openEuler x86 (310p)
- openEuler x86 (910b, ACL Graph)
- openEuler aarch64 (310p)
- openEuler aarch64 (910b, ACL Graph)
UI:
- UI

hexagon: fix CPY fence bug (#28033)
Website:
- https://llama.app
Attestations:
- https://github.com/ggml-org/llama.cpp/attestations/44046740
macOS/iOS:
- macOS Apple Silicon (arm64)
- macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED
- macOS Intel (x64)
- iOS XCFramework
Linux:
- Ubuntu x64 (CPU)
- Ubuntu arm64 (CPU)
- Ubuntu s390x (CPU)
- Ubuntu x64 (Vulkan)
- Ubuntu arm64 (Vulkan)
- Ubuntu x64 (ROCm 7.14)
- Ubuntu x64 (OpenVINO)
- Ubuntu x64 (SYCL FP32)
- Ubuntu x64 (SYCL FP16)
Android:
- Android arm64 (CPU)
Windows:
- Windows x64 (CPU)
- Windows arm64 (CPU)
- Windows arm64 (OpenCL Adreno)
- Windows x64 (CUDA 12) - CUDA 12.4 DLLs
- Windows x64 (CUDA 13) - CUDA 13.3 DLLs
- Windows arm64 (CUDA 13) (preview) - CUDA 13.4 DLLs
- Windows x64 (Vulkan)
- Windows x64 (OpenVINO)
- Windows x64 (SYCL)
- Windows x64 (ROCm 7.14)
openEuler:
- DISABLED
- openEuler x86 (310p)
- openEuler x86 (910b, ACL Graph)
- openEuler aarch64 (310p)
- openEuler aarch64 (910b, ACL Graph)
UI:
- UI

ggml: allow passing alloc dependencies in graph_optimize (#27301)
- ggml: allow passing alloc dependencies in graph_optimize
- add alloc dep tests
- add TODO about using flat array
Website:
- https://llama.app
Attestations:
- https://github.com/ggml-org/llama.cpp/attestations/43919110
macOS/iOS:
- macOS Apple Silicon (arm64)
- macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED
- macOS Intel (x64)
- iOS XCFramework
Linux:
- Ubuntu x64 (CPU)
- Ubuntu arm64 (CPU)
- Ubuntu s390x (CPU)
- Ubuntu x64 (Vulkan)
- Ubuntu arm64 (Vulkan)
- Ubuntu x64 (ROCm 7.14)
- Ubuntu x64 (OpenVINO)
- Ubuntu x64 (SYCL FP32)
- Ubuntu x64 (SYCL FP16)
Android:
- Android arm64 (CPU)
Windows:
- Windows x64 (CPU)
- Windows arm64 (CPU)
- Windows arm64 (OpenCL Adreno)
- Windows x64 (CUDA 12) - CUDA 12.4 DLLs
- Windows x64 (CUDA 13) - CUDA 13.3 DLLs
- Windows arm64 (CUDA 13) (preview) - CUDA 13.4 DLLs
- Windows x64 (Vulkan)
- Windows x64 (OpenVINO)
- Windows x64 (SYCL)
- Windows x64 (ROCm 7.14)
openEuler:
- DISABLED
- openEuler x86 (310p)
- openEuler x86 (910b, ACL Graph)
- openEuler aarch64 (310p)
- openEuler aarch64 (910b, ACL Graph)
UI:
- UI

bench: add --tensor-read-lazy (#27881)
- bench: add --tensor-read-lazy
- rm the alias
- rename to LLAMA_LAZY_MODE_*
Website:
- https://llama.app
Attestations:
- https://github.com/ggml-org/llama.cpp/attestations/43739963
macOS/iOS:
- macOS Apple Silicon (arm64)
- macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED
- macOS Intel (x64)
- iOS XCFramework
Linux:
- Ubuntu x64 (CPU)
- Ubuntu arm64 (CPU)
- Ubuntu s390x (CPU)
- Ubuntu x64 (Vulkan)
- Ubuntu arm64 (Vulkan)
- Ubuntu x64 (ROCm 7.14)
- Ubuntu x64 (OpenVINO)
- Ubuntu x64 (SYCL FP32)
- Ubuntu x64 (SYCL FP16)
Android:
- Android arm64 (CPU)
Windows:
- Windows x64 (CPU)
- Windows arm64 (CPU)
- Windows arm64 (OpenCL Adreno)
- Windows x64 (CUDA 12) - CUDA 12.4 DLLs
- Windows x64 (CUDA 13) - CUDA 13.3 DLLs
- Windows arm64 (CUDA 13) (preview) - CUDA 13.4 DLLs
- Windows x64 (Vulkan)
- Windows x64 (OpenVINO)
- Windows x64 (SYCL)
- Windows x64 (ROCm 7.14)
openEuler:
- DISABLED
- openEuler x86 (310p)
- openEuler x86 (910b, ACL Graph)
- openEuler aarch64 (310p)
- openEuler aarch64 (910b, ACL Graph)
UI:
- UI

tests : run test-save-load-state across all architectures (#27755)
- tests : run test-save-load-state across all architectures
test-save-load-state previously only ran in ctest against a single
downloaded model (tinyllamas/stories15M), i.e. only the llama arch.
Add a --models DIR mode to test-save-load-state that runs the full
save/load suite over every *.gguf in a directory, reporting a
per-model PASS/FAIL and exiting non-zero if any model fails, and wire
a ctest to run it over all architectures using the existing
generate-models fixture (test-llama-archs). The single-model -m mode
is preserved (still used by ci/run.sh).
Also bump the dummy-model training context in test-llama-archs from
128 to 256 so that the per-sequence context (which is padded up to a
multiple of 256) no longer exceeds n_ctx_train and emits the
"possible training context overflow" warning.
The test is expected to fail until the affected arches are fixed:
deepseek4 (host seq-copy), gemma2/gpt-oss/lfm2 (device seq-copy),
minimax-01 (state load). It aborts at the first arch that crashes.
Assisted-by: pi:llama.cpp/Qwen3.8-27B
- tests : match dummy DSA indexer to fused Lightning Indexer kernel
The dummy DSA indexer (deepseek32, glm-dsa, ...) used key_length=64 and head_count=1, so the fused Lightning Indexer op's q tensor was shaped [64, 1, ...]. The Metal fused kernel is fixed to DK=128, NH=64, so it rejected the op and the scheduler fell back to CPU, emitting a 'layer assigned to MTL but Lightning Indexer on CPU' warning. Bump key_length to 128 and the DSA head_count to 64 so the fused op runs on the GPU.
Assisted-by: pi:llama.cpp/Qwen3.8-27B
- tests : add --help and document -o in test-llama-archs
Add a --help/-h flag to test-llama-archs and list the existing -o/--out option in the usage text, which was previously missing.
Assisted-by: pi:llama.cpp/Qwen3.8-27B
- tests : use 64 indexer heads for deepseek4
deepseek4's indexer head count was set to n_head (8), which does not match the fused Lightning Indexer kernel's fixed NH=64, so the fused op fell back to the CPU backend and emitted a device-mismatch warning. Give it the same fixed 64 as the other indexer archs by dropping it from the n_head ternary (only minimax-m3 keeps n_head, since it does not use the fused Lightning Indexer op).
Assisted-by: pi:llama.cpp/Qwen3.8-27B
- tests : fix dsv4 save-load n_stream mismatch
The dsv4 KV cache keeps per-sequence KV/state streams even in unified mode, so its n_stream equals n_seq_max. The test saved the state in the baseline with n_seq_max=1 but loaded it in the seq-copy tests with n_seq_max=2, so state_read threw an n_stream mismatch. Use n_seq_max=2 in the baseline and state-load tests so the save and load agree.
Assisted-by: pi:llama.cpp/Qwen3.8-27B
- context : relax on-device seq-copy chunk alignment
The on-device state seq copy (llama_state_seq_set_data with LLAMA_STATE_SEQ_FLAGS_ON_DEVICE) copied the write-side cpy tensors to the read-side targets 1:1 by index, requiring the writer and reader to emit the same number of chunks in the same order with the same per-chunk sizes. state_write_data chunks per cell-range while state_read_data chunks contiguous-or-per-cell, so the counts diverged for non-contiguous sources (dsv4, SWA) and the copy aborted with "memory buffer mismatch".
All state writers and readers enumerate the same logical data in the same order, differing only in chunking. Copy the flat write-side data into the read-side targets with a byte cursor that walks both tensor lists across their boundaries, so the chunking no longer needs to match. Keep the total-size guard; drop the n_tensors equality check.
Assisted-by: pi:llama.cpp/Qwen3.8-27B
- model : fix dangling hparams ref in minimax-01 LA graph input
llm_graph_input_la stored const llama_hparams & hparams, bound to the llm_graph_params temporary in llama_context::process_ubatch. The input object outlives that temporary (it is kept in llm_graph_result::inputs for graph reuse), so set_input() read des

llama : add --n-cpu-ffn option (#26622)
- common : dedupe --n-cpu-moe / --spec-draft-n-cpu-moe override loops
- common : add --n-cpu-ffn to CPU-offload dense FFN weights of first N layers
- common : generalize llm_ffn_block_regex over the FFN regex, drop TODO
Website:
- https://llama.app
Attestations:
- https://github.com/ggml-org/llama.cpp/attestations/43362872
macOS/iOS:
- macOS Apple Silicon (arm64)
- macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED
- macOS Intel (x64)
- iOS XCFramework
Linux:
- Ubuntu x64 (CPU)
- Ubuntu arm64 (CPU)
- Ubuntu s390x (CPU)
- Ubuntu x64 (Vulkan)
- Ubuntu arm64 (Vulkan)
- Ubuntu x64 (ROCm 7.14)
- Ubuntu x64 (OpenVINO)
- Ubuntu x64 (SYCL FP32)
- Ubuntu x64 (SYCL FP16)
Android:
- Android arm64 (CPU)
Windows:
- Windows x64 (CPU)
- Windows arm64 (CPU)
- Windows arm64 (OpenCL Adreno)
- Windows x64 (CUDA 12) - CUDA 12.4 DLLs
- Windows x64 (CUDA 13) - CUDA 13.3 DLLs
- Windows arm64 (CUDA 13) (preview) - CUDA 13.4 DLLs
- Windows x64 (Vulkan)
- Windows x64 (OpenVINO)
- Windows x64 (SYCL)
- Windows x64 (ROCm 7.14)
openEuler:
- DISABLED
- openEuler x86 (310p)
- openEuler x86 (910b, ACL Graph)
- openEuler aarch64 (310p)
- openEuler aarch64 (910b, ACL Graph)
UI:
- UI

metal : per-device tuned (Q, NE) for flash-attn vec (#26570)
- metal : per-device tuned (Q, NE) for flash-attn vec (#25750)
- rebase Q-generic FA vec body from 01dc936 (#23114)
- add 53 f16 (Q,NE) flash-attn vec instantiations (vec 80 -> 133)
- add FA vec (Q,NE) tuning table + dispatch wiring + SMEM cap fallback
- add FA vec (Q,NE) perf sweep
- fill tuning result
- fold family table into a per-family representative SKU
- refactor tuning result format
- extend FA vec tuning to quantized KV caches
- sync fa vec tuner bucketing with runtime, use pointwise tuning regret
- update tuned table
- format and cleanup
- prefix fa_vec tuning procs with ggml_backend_metal_tuning_, drop unused fa_vec_override_active
- add device id -> token lookup for the offline tuning tool
- add ggml-metal-tuning skeleton
- add op-agnostic perf cell + median timing for the tuner
- add FA-vec graph build + tensor init to the tuner
- tools : add FA-vec (Q,NE) sweep, compression and table emit
- cool down and re-measure the dirty window on thermal drift
- test-backend-ops : replace the FA vec tune mode with a bounded (Q,NE) slice
- tools : document the Metal tuner, point the table comment at it
- abort on unknown KV type, single-source fa_vec_legal_ne
- cleanup
- honor -o in the FA vec (Q,NE) slice
- retune FA-vec (Q, NE) under a pointwise no-harm gate
- cont : add fa-vec tunings for M1 Pro, M2 Ultra, M5 Max
Co-authored-by: Georgi Gerganov ggerganov@gmail.com
Website:
- https://llama.app
Attestations:
- https://github.com/ggml-org/llama.cpp/attestations/42707049
macOS/iOS:
- macOS Apple Silicon (arm64)
- macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED
- macOS Intel (x64)
- iOS XCFramework
Linux:
- Ubuntu x64 (CPU)
- Ubuntu arm64 (CPU)
- Ubuntu s390x (CPU)
- Ubuntu x64 (Vulkan)
- Ubuntu arm64 (Vulkan)
- Ubuntu x64 (ROCm 7.14)
- Ubuntu x64 (OpenVINO)
- Ubuntu x64 (SYCL FP32)
- Ubuntu x64 (SYCL FP16)
Android:
- Android arm64 (CPU)
Windows:
- Windows x64 (CPU)
- Windows arm64 (CPU)
- Windows arm64 (OpenCL Adreno)
- Windows x64 (CUDA 12) - CUDA 12.4 DLLs
- Windows x64 (CUDA 13) - CUDA 13.3 DLLs
- Windows arm64 (CUDA 13) (preview) - CUDA 13.4 DLLs
- Windows x64 (Vulkan)
- Windows x64 (OpenVINO)
- Windows x64 (SYCL)
- Windows x64 (ROCm 7.14)
openEuler:
- DISABLED
- openEuler x86 (310p)
- openEuler x86 (910b, ACL Graph)
- openEuler aarch64 (310p)
- openEuler aarch64 (910b, ACL Graph)
UI:
- UI

model : support MTP in GLM-4.5-Air (#26534)
Website:
- https://llama.app
Attestations:
- https://github.com/ggml-org/llama.cpp/attestations/42447665
macOS/iOS:
- macOS Apple Silicon (arm64)
- macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED
- macOS Intel (x64)
- iOS XCFramework
Linux:
- Ubuntu x64 (CPU)
- Ubuntu arm64 (CPU)
- Ubuntu s390x (CPU)
- Ubuntu x64 (Vulkan)
- Ubuntu arm64 (Vulkan)
- Ubuntu x64 (ROCm 7.14)
- Ubuntu x64 (OpenVINO)
- Ubuntu x64 (SYCL FP32)
- Ubuntu x64 (SYCL FP16)
Android:
- Android arm64 (CPU)
Windows:
- Windows x64 (CPU)
- Windows arm64 (CPU)
- Windows arm64 (OpenCL Adreno)
- Windows x64 (CUDA 12) - CUDA 12.4 DLLs
- Windows x64 (CUDA 13) - CUDA 13.3 DLLs
- Windows arm64 (CUDA 13) (preview) - CUDA 13.4 DLLs
- Windows x64 (Vulkan)
- Windows x64 (OpenVINO)
- Windows x64 (SYCL)
- Windows x64 (ROCm 7.14)
openEuler:
- DISABLED
- openEuler x86 (310p)
- openEuler x86 (910b, ACL Graph)
- openEuler aarch64 (310p)
- openEuler aarch64 (910b, ACL Graph)
UI:
- UI

common: json.h: fix clang lto (#27575)
Website:
- https://llama.app
Attestations:
- https://github.com/ggml-org/llama.cpp/attestations/42368523
macOS/iOS:
- macOS Apple Silicon (arm64)
- macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED
- macOS Intel (x64)
- iOS XCFramework
Linux:
- Ubuntu x64 (CPU)
- Ubuntu arm64 (CPU)
- Ubuntu s390x (CPU)
- Ubuntu x64 (Vulkan)
- Ubuntu arm64 (Vulkan)
- Ubuntu x64 (ROCm 7.14)
- Ubuntu x64 (OpenVINO)
- Ubuntu x64 (SYCL FP32)
- Ubuntu x64 (SYCL FP16)
Android:
- Android arm64 (CPU)
Windows:
- Windows x64 (CPU)
- Windows arm64 (CPU)
- Windows arm64 (OpenCL Adreno)
- Windows x64 (CUDA 12) - CUDA 12.4 DLLs
- Windows x64 (CUDA 13) - CUDA 13.3 DLLs
- Windows arm64 (CUDA 13) (preview) - CUDA 13.4 DLLs
- Windows x64 (Vulkan)
- Windows x64 (OpenVINO)
- Windows x64 (SYCL)
- Windows x64 (ROCm 7.14)
openEuler:
- DISABLED
- openEuler x86 (310p)
- openEuler x86 (910b, ACL Graph)
- openEuler aarch64 (310p)
- openEuler aarch64 (910b, ACL Graph)
UI:
- UI

TP: enable tensor split for LFM2/LFM2MOE (#26993)
Assisted-by: deepseek-v4-flash
Website:
- https://llama.app
Attestations:
- https://github.com/ggml-org/llama.cpp/attestations/42096995
macOS/iOS:
- macOS Apple Silicon (arm64)
- macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED
- macOS Intel (x64)
- iOS XCFramework
Linux:
- Ubuntu x64 (CPU)
- Ubuntu arm64 (CPU)
- Ubuntu s390x (CPU)
- Ubuntu x64 (Vulkan)
- Ubuntu arm64 (Vulkan)
- Ubuntu x64 (ROCm 7.14)DISABLED
- Ubuntu x64 (OpenVINO)
- Ubuntu x64 (SYCL FP32)
- Ubuntu x64 (SYCL FP16)
Android:
- Android arm64 (CPU)
Windows:
- Windows x64 (CPU)
- Windows arm64 (CPU)
- Windows arm64 (OpenCL Adreno)
- Windows x64 (CUDA 12) - CUDA 12.4 DLLs
- Windows x64 (CUDA 13) - CUDA 13.3 DLLs
- Windows arm64 (CUDA 13) (preview) - CUDA 13.4 DLLs
- Windows x64 (Vulkan)
- Windows x64 (OpenVINO)
- Windows x64 (SYCL)
- Windows x64 (ROCm 7.14)
openEuler:
- DISABLED
- openEuler x86 (310p)
- openEuler x86 (910b, ACL Graph)
- openEuler aarch64 (310p)
- openEuler aarch64 (910b, ACL Graph)
UI:
- UI

metal : clamp K extent in tensor API mat-mat kernel for K not a multiple of 32 (#27450)
The Tensor API mat-mat path of kernel_mul_mm (GGML_METAL_HAS_TENSOR) fed a
static K=32 tile to the matmul2d op on every iteration. On the last, partial
K tile (ne00 % 32 != 0) the src1 slice extends past the K extent of the
tensor, and the op reads those out-of-bounds elements (undefined behavior per
the MSL specification, section 2.22.2). Depending on stale memory contents,
this corrupted the result or produced NaN.
Make the matmul2d op use dynamic_extent for K, and clamp the K extent of both
operand tensor views to the remaining valid K range (min(32, K - loop_k)) per
iteration, so the op reads exactly the valid K range on every iteration
(mirroring the tail handling of the MPP matmul2d examples). On K-aligned
inputs the clamp degenerates to the full 32-wide tile: the only difference
from the static-K op is that the dynamic-K op derives K from the operand
extents and edge-checks the tile against the tensor extents (a handful of
integer ops per iteration).
Add test-backend-ops MUL_MAT cases with K not a multiple of 32 to exercise
the unaligned K path.
Assisted-by: pi:llama.cpp/Qwen3.8-27B
Website:
- https://llama.app
Attestations:
- https://github.com/ggml-org/llama.cpp/attestations/42040575
macOS/iOS:
- macOS Apple Silicon (arm64)
- macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED
- macOS Intel (x64)
- iOS XCFramework
Linux:
- Ubuntu x64 (CPU)
- Ubuntu arm64 (CPU)
- Ubuntu s390x (CPU)
- Ubuntu x64 (Vulkan)
- Ubuntu arm64 (Vulkan)
- Ubuntu x64 (ROCm 7.14)DISABLED
- Ubuntu x64 (OpenVINO)
- Ubuntu x64 (SYCL FP32)
- Ubuntu x64 (SYCL FP16)
Android:
- Android arm64 (CPU)
Windows:
- Windows x64 (CPU)
- Windows arm64 (CPU)
- Windows arm64 (OpenCL Adreno)
- Windows x64 (CUDA 12) - CUDA 12.4 DLLs
- Windows x64 (CUDA 13) - CUDA 13.3 DLLs
- Windows arm64 (CUDA 13) (preview) - CUDA 13.4 DLLs
- Windows x64 (Vulkan)
- Windows x64 (OpenVINO)
- Windows x64 (SYCL)
- Windows x64 (ROCm 7.14)
openEuler:
- DISABLED
- openEuler x86 (310p)
- openEuler x86 (910b, ACL Graph)
- openEuler aarch64 (310p)
- openEuler aarch64 (910b, ACL Graph)
UI:
- UI

mtmd: add mtmd_bitmap_set_mergeable (#27348)
Website:
- https://llama.app
macOS/iOS:
- macOS Apple Silicon (arm64)
- macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED
- macOS Intel (x64)
- iOS XCFramework
Linux:
- Ubuntu x64 (CPU)
- Ubuntu arm64 (CPU)
- Ubuntu s390x (CPU)
- Ubuntu x64 (Vulkan)
- Ubuntu arm64 (Vulkan)
- Ubuntu x64 (ROCm 7.14)DISABLED
- Ubuntu x64 (OpenVINO)
- Ubuntu x64 (SYCL FP32)
- Ubuntu x64 (SYCL FP16)
Android:
- Android arm64 (CPU)
Windows:
- Windows x64 (CPU)
- Windows arm64 (CPU)
- Windows arm64 (OpenCL Adreno)
- Windows x64 (CUDA 12) - CUDA 12.4 DLLs
- Windows x64 (CUDA 13) - CUDA 13.3 DLLs
- Windows arm64 (CUDA 13) (preview) - CUDA 13.4 DLLs
- Windows x64 (Vulkan)
- Windows x64 (OpenVINO)
- Windows x64 (SYCL)
- Windows x64 (ROCm 7.14)
openEuler:
- DISABLED
- openEuler x86 (310p)
- openEuler x86 (910b, ACL Graph)
- openEuler aarch64 (310p)
- openEuler aarch64 (910b, ACL Graph)
UI:
- UI

ci : Update OpenVINO to 2026.3, skip nemotron-h rollback test (#27292)
- update to ov-2026.3, update device drivers
- ci: skip nemotron-h rollback test on OpenVINO
The OpenVINO backend does not support SSM_SCAN, so the Nemotron-H recurrent state rollback graph is split and cannot preserve the recurrent cache output shape. Keep the test enabled for other backends and retain the qwen35 OpenVINO rollback coverage.
Co-authored-by: ravi9 ravi.panchumarthy@intel.com
Website:
- https://llama.app
macOS/iOS:
- macOS Apple Silicon (arm64)
- macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED
- macOS Intel (x64)
- iOS XCFramework
Linux:
- Ubuntu x64 (CPU)
- Ubuntu arm64 (CPU)
- Ubuntu s390x (CPU)
- Ubuntu x64 (Vulkan)
- Ubuntu arm64 (Vulkan)
- Ubuntu x64 (ROCm 7.14)DISABLED
- Ubuntu x64 (OpenVINO)
- Ubuntu x64 (SYCL FP32)
- Ubuntu x64 (SYCL FP16)
Android:
- Android arm64 (CPU)
Windows:
- Windows x64 (CPU)
- Windows arm64 (CPU)
- Windows arm64 (OpenCL Adreno)
- Windows x64 (CUDA 12) - CUDA 12.4 DLLs
- Windows x64 (CUDA 13) - CUDA 13.3 DLLs
- Windows arm64 (CUDA 13) (preview) - CUDA 13.4 DLLs
- Windows x64 (Vulkan)
- Windows x64 (OpenVINO)
- Windows x64 (SYCL)
- Windows x64 (ROCm 7.14)
openEuler:
- DISABLED
- openEuler x86 (310p)
- openEuler x86 (910b, ACL Graph)
- openEuler aarch64 (310p)
- openEuler aarch64 (910b, ACL Graph)
UI:
- UI

cuda : skip UMA override for HIP builds (#27083)
AMD APUs report accurate memory via hipMemGetInfo. Using
MemAvailable over-promises on small-carveout systems.
fixes #18159
Website:
- https://llama.app
macOS/iOS:
- macOS Apple Silicon (arm64)
- macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED
- macOS Intel (x64)
- iOS XCFramework
Linux:
- Ubuntu x64 (CPU)
- Ubuntu arm64 (CPU)
- Ubuntu s390x (CPU)
- Ubuntu x64 (Vulkan)
- Ubuntu arm64 (Vulkan)
- Ubuntu x64 (ROCm 7.14)DISABLED
- Ubuntu x64 (OpenVINO)
- Ubuntu x64 (SYCL FP32)
- Ubuntu x64 (SYCL FP16)
Android:
- Android arm64 (CPU)
Windows:
- Windows x64 (CPU)
- Windows arm64 (CPU)
- Windows arm64 (OpenCL Adreno)
- Windows x64 (CUDA 12) - CUDA 12.4 DLLs
- Windows x64 (CUDA 13) - CUDA 13.3 DLLs
- Windows arm64 (CUDA 13) (preview) - CUDA 13.4 DLLs
- Windows x64 (Vulkan)
- Windows x64 (OpenVINO)
- Windows x64 (SYCL)
- Windows x64 (ROCm 7.14)
openEuler:
- DISABLED
- openEuler x86 (310p)
- openEuler x86 (910b, ACL Graph)
- openEuler aarch64 (310p)
- openEuler aarch64 (910b, ACL Graph)
UI:
- UI

model : remove some ggml_concat (#27176)
Co-authored-by: Xuan Son Nguyen son@huggingface.co
Website:
- https://llama.app
macOS/iOS:
- macOS Apple Silicon (arm64)
- macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED
- macOS Intel (x64)
- iOS XCFramework
Linux:
- Ubuntu x64 (CPU)
- Ubuntu arm64 (CPU)
- Ubuntu s390x (CPU)
- Ubuntu x64 (Vulkan)
- Ubuntu arm64 (Vulkan)
- Ubuntu x64 (ROCm 7.14)DISABLED
- Ubuntu x64 (OpenVINO)
- Ubuntu x64 (SYCL FP32)
- Ubuntu x64 (SYCL FP16)
Android:
- Android arm64 (CPU)
Windows:
- Windows x64 (CPU)
- Windows arm64 (CPU)
- Windows arm64 (OpenCL Adreno)
- Windows x64 (CUDA 12) - CUDA 12.4 DLLs
- Windows x64 (CUDA 13) - CUDA 13.3 DLLs
- Windows arm64 (CUDA 13) (preview) - CUDA 13.4 DLLs
- Windows x64 (Vulkan)
- Windows x64 (OpenVINO)
- Windows x64 (SYCL)
- Windows x64 (ROCm 7.14)
openEuler:
- DISABLED
- openEuler x86 (310p)
- openEuler x86 (910b, ACL Graph)
- openEuler aarch64 (310p)
- openEuler aarch64 (910b, ACL Graph)
UI:
- UI

model: add Kimi-K3 text model (#26185)
- model: add Kimi-K3 text model
Hybrid KDA (linear) + MLA (full) attention as in Kimi-Linear-48B, plus five
things that architecture does not have:
1. cross-layer residual attention (attn_res_block_size)
2. latent MoE (routed experts run at n_expert_latent)
3. situ activation (replaces SwiGLU everywhere)
4. MLA output gate (sigmoid gate before o_proj)
5. full-rank KDA gate (single ssm_g instead of ssm_g_a/ssm_g_b)
K3's text_config reports KimiLinearForCausalLM - the older 48B architecture -
so get_model_architecture routes on the top-level name instead.
The KDA decay gate has two forms, selected by linear_attn_config's
gate_lower_bound. It is not a clamp: when set it swaps the activation entirely
(fla/ops/kda/gate.py), from -exp(A_log)softplus(x) to
lower_boundsigmoid(exp(A_log)*x). K3 sets it to -5.0; kimi-linear leaves it
unset, so that path is unchanged.
Cross-layer residuals reuse ggml_dsv4_hc_pre for the weighted sum. That op is
CPU + CUDA only, so Metal/Vulkan will fall back per-node until those kernels
exist.
The routed experts ship as compressed-tensors "mxfp4-pack-quantized". That is
bit-compatible with ggml's MXFP4 - same E2M1 code assignment, same E8M0 scale
byte, only the nibble positions within a block differ - so they are repacked
rather than dequantized, losslessly and without a ~5.5 TB bf16 round-trip.
The repack is built lazily because gguf_writer holds every added tensor until
the final write. DeepSeek-V4 was already doing the identical bit-shuffling, so
it now shares the helper.
Verified against Moonshot's own code path (transformers + fla's Triton KDA
kernels) on a tiny model exercising every K3-specific feature. Final-position
logits vs the fp32 reference: 6.7e-05 rel / corr 1.00000000 for both the
chunked and the recurrent delta-net path. MXFP4 blocks dequantize to the source
weights with 0.0e+00 error.
Assisted-By: Claude Opus 5 (1M context) noreply@anthropic.com
- model: fix ty errors in the Kimi-K3 converter
- _res_parts buffers (kind, tensor) pairs, not bare tensors
- get_tensors must return an Iterator, matching ModelBase
- LazyBase's func takes one argument, so pass the expert loaders through
args instead of the closure
- borrowing KimiLinearModel.set_vocab from an unrelated TextModel is
deliberate and safe, but not expressible in the signature
No behaviour change: the MXFP4 repack still dequantizes to the source weights
with 0.0e+00 error and end-to-end logits are unchanged (8.386e-03 rel,
corr 0.99996630).
Assisted-By: Claude Opus 5 (1M context) noreply@anthropic.com
- Update conversion/kimi_k3.py
Co-authored-by: Boris Dvorkin b_dvorkin@niuitmo.ru
- Increase LLAMA_MAX_EXPERTS from 512 to 1024
- tests : support for Kimi K3 in archs test
- chat : add Kimi K3 chat format (reasoning, content, typed tool calls)
K3's assistant output is an XTML-ish tagged format built by the template's
open_tag/close_tag macros. Two properties break generic parsing:
1. The generation prompt ends with open_tag('think'), so the completion
starts inside the think section with no opening marker in the output
(thinking_forced_open).
2. Only <|open|>/<|close|>/<|sep|>/<|end_of_msg|> are special tokens; tag
names ("think", "response", "message") are ordinary text tokens.
Adds common_chat_params_init_kimi_k3 (PEG_NATIVE) with detection on the
marker trio, reasoning extraction, response unwrapping, and tool-call
parsing of the tools/call/argument tag structure with argument types
taken from the tool schema. Includes the K3 chat template fixture and 9
test-chat cases derived from real generations of the full 2.8T model.
Verified end-to-end against Kimi-K3-Q2_K (GrEarl/Kimi-K3-GGUF) on 8x B200:
content, reasoning_content, streaming deltas, and tool_calls all correct;
finish_reason stop/tool_calls as appropriate.
Co-Authored-By: Claude Fable 5 noreply@anthropic.com
- chat : add message_delimiters for Kimi K3
Per-role message-start markers for token-level span splitting. User and
assistant mess

model : add support for MiniMaxText01ForCausalLM and MiniMaxM1ForCausalLM (#27018)
- llama : support for MiniMax-Text-01 model
- chore : renames to match the other MiniMax models
- model : add logits mask as MiniMax-Text-01 embeddings tensor has zero-valued embeddings for tokens >= 200032 that produce zero logits disrupting the token sampling process
- llama : replace hardcoded conditions with hparams.is_recr()
- model : used build_rs() for recurrent state management
- chore : code cleanup
- model : optimized MiniMax-Text-01 by removing the state tranpose operations
- chore : removed unnecessary ggml_cont() in MiniMax-Text-01 implementation
- llama : add generic logits mask graph input
- model : permuted diag_decay dimensions to avoid doing it inside MiniMax-Text-01 graph
- chore : code cleanup
- chore : code cleanup
- model : use token positions when calculating MiniMax-Text-01 decay tensors
- convert : add support for MiniMaxM1ForCausalLM as it seems to be the same as MiniMaxText01ForCausalLM
- chat : add jinja template for MiniMax-M1
Co-authored-by: QscQ qscqesze@gmail.com
- chore : code cleanup
- tests : MINIMAX_01-related fixes
- chore : silence Python lint errors
- vocab : remove unnecessary vocab type
- convert : update MiniMaxText01Model conversion to use yield when modifying tensors
- convert : suppress tokens with zero-valued embeddings during MiniMax-Text-01 conversion
- llama : removed logits mask - no longer necessary as token suppression is used instead
- model : use common functions to make MiniMax-Text-01 implementation more concise
Co-authored-by: Sigbjørn Skjæret sigbjorn.skjaeret@huggingface.co
- model : use common functions to make MiniMax-Text-01 implementation more concise
Co-authored-by: Sigbjørn Skjæret sigbjorn.skjaeret@huggingface.co
- convert : override non-working built-in chat template during conversion
- tests : skip arch MINIMAX_01 tests for WebGPU backend (it breaks again)
Co-authored-by: Stanisław Szymczyk sszymczy@gmail.com
Co-authored-by: QscQ qscqesze@gmail.com
Co-authored-by: Sigbjørn Skjæret sigbjorn.skjaeret@huggingface.co
Website:
- https://llama.app
macOS/iOS:
- macOS Apple Silicon (arm64)
- macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED
- macOS Intel (x64)
- iOS XCFramework
Linux:
- Ubuntu x64 (CPU)
- Ubuntu arm64 (CPU)
- Ubuntu s390x (CPU)
- Ubuntu x64 (Vulkan)
- Ubuntu arm64 (Vulkan)
- Ubuntu x64 (ROCm 7.14)DISABLED
- Ubuntu x64 (OpenVINO)
- Ubuntu x64 (SYCL FP32)
- Ubuntu x64 (SYCL FP16)
Android:
- Android arm64 (CPU)
Windows:
- Windows x64 (CPU)
- Windows arm64 (CPU)
- Windows arm64 (OpenCL Adreno)
- Windows x64 (CUDA 12) - CUDA 12.4 DLLs
- Windows x64 (CUDA 13) - CUDA 13.3 DLLs
- Windows arm64 (CUDA 13) (preview) - CUDA 13.4 DLLs
- Windows x64 (Vulkan)
- Windows x64 (OpenVINO)
- Windows x64 (SYCL)
- Windows x64 (ROCm 7.14)
openEuler:
- DISABLED
- openEuler x86 (310p)
- openEuler x86 (910b, ACL Graph)
- openEuler aarch64 (310p)
- openEuler aarch64 (910b, ACL Graph)
UI:
- UI

dflash : clarify output logging of target_layer_ids (#27013)
This commit tries to make the logging of target_layer_ids a bit clearer
and easier to read.
Currently the output generated looks like this:
0.00.468.624 D load_arch_hparams: DFlash extract_layers = [0.00.468.626 D 2, 0.00.468.626 D 6, 0.00.468.626 D 20,
0.00.468.626 D 30, 0.00.468.627 D 42, 0.00.468.627 D 520.00.468.627 D ]
With the changes in the commit the output will be:
0.00.522.765 D load_arch_hparams: DFlash extract_layers = [2, 6, 20, 30, 42, 52]
Website:
- https://llama.app
macOS/iOS:
- macOS Apple Silicon (arm64)
- macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED
- macOS Intel (x64)
- iOS XCFramework
Linux:
- Ubuntu x64 (CPU)
- Ubuntu arm64 (CPU)
- Ubuntu s390x (CPU)
- Ubuntu x64 (Vulkan)
- Ubuntu arm64 (Vulkan)
- Ubuntu x64 (ROCm 7.14)DISABLED
- Ubuntu x64 (OpenVINO)
- Ubuntu x64 (SYCL FP32)
- Ubuntu x64 (SYCL FP16)
Android:
- Android arm64 (CPU)
Windows:
- Windows x64 (CPU)
- Windows arm64 (CPU)
- Windows arm64 (OpenCL Adreno)
- Windows x64 (CUDA 12) - CUDA 12.4 DLLs
- Windows x64 (CUDA 13) - CUDA 13.3 DLLs
- Windows arm64 (CUDA 13) (preview) - CUDA 13.4 DLLs
- Windows x64 (Vulkan)
- Windows x64 (OpenVINO)
- Windows x64 (SYCL)
- Windows x64 (ROCm 7.14)
openEuler:
- DISABLED
- openEuler x86 (310p)
- openEuler x86 (910b, ACL Graph)
- openEuler aarch64 (310p)
- openEuler aarch64 (910b, ACL Graph)
UI:
- UI

chat : tighten bare function parsing for Qwen models (#26793)
Website:
- https://llama.app
macOS/iOS:
- macOS Apple Silicon (arm64)
- macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED
- macOS Intel (x64)
- iOS XCFramework
Linux:
- Ubuntu x64 (CPU)
- Ubuntu arm64 (CPU)
- Ubuntu s390x (CPU)
- Ubuntu x64 (Vulkan)
- Ubuntu arm64 (Vulkan)
- Ubuntu x64 (ROCm 7.14)
- Ubuntu x64 (OpenVINO)
- Ubuntu x64 (SYCL FP32)
- Ubuntu x64 (SYCL FP16)
Android:
- Android arm64 (CPU)
Windows:
- Windows x64 (CPU)
- Windows arm64 (CPU)
- Windows arm64 (OpenCL Adreno)
- Windows x64 (CUDA 12) - CUDA 12.4 DLLs
- Windows x64 (CUDA 13) - CUDA 13.3 DLLs
- Windows arm64 (CUDA 13) (preview) - CUDA 13.4 DLLs
- Windows x64 (Vulkan)
- Windows x64 (OpenVINO)
- Windows x64 (SYCL)
- Windows x64 (ROCm 7.14)
openEuler:
- DISABLED
- openEuler x86 (310p)
- openEuler x86 (910b, ACL Graph)
- openEuler aarch64 (310p)
- openEuler aarch64 (910b, ACL Graph)
UI:
- UI

mtmd: support pocket-tts (#26871)
- adapt the api
- text model ok
- working impl, need verify and clean up
- mtmd: build the pocket-tts transposed convolutions as GEMM + col2im
ggml_conv_transpose_1d has no grouped mode, so the depthwise upsample
was built as one convolution and one concat per channel, which floods
the graph with small nodes and makes kernel launches dominate the
decoder.
Fold both cases into the column form the seanet decoder already needs:
the general case reshapes the kernel to [IC, K * OC] and matmuls it
with the input, the depthwise case batches a matmul over the channels
so a step scales its own kernel. A single col2im_1d then scatter-adds
the columns back to the signal, with the same shape as before, so the
overlap-add tail, the streaming state and the bias are untouched.
Generation time per frame drops by 80% on CUDA and by 50% on CPU. The
output matches the previous implementation sample for sample, with a
correlation of 0.999994 and identical frame counts.
- flow_temp + frames_after_eos
- chunking
- mtmd: carry the remaining pocket-tts per-pack settings
The language packs also tune the end-of-speech padding and the padding
of short prompts, next to the temperature already carried in the
mmproj: french_24l asks for 8 tail frames instead of the guessed 3,
english_2026-01 asks for short prompts to be padded with spaces.
Write both in the mmproj as clip.gen.audio.frames_after_eos and
clip.gen.audio.pad_short_text, keyed on the pack in the conversion
script like the temperature. The loader keeps them optional, so a
mmproj without them behaves as before. Map semicolons to commas for
every pack instead, the reference only asks for it on three of them and
it costs nothing elsewhere.
Existing mmproj files must be converted again to carry the two keys.
On a long french text the port now lands within 2% of the reference:
22.96s against 23.44s, with the same peak level and the same amount of
silence.
- clip.gen.audio.model_variant
- clean up code comments
- nit: drop the dead flow_temp hparam, the pack table holds the default
- update docs
- address security problems
- less invasive base.py
- lint
- add mtmd_gen_inp_default
- add docs
- rm gen_flow_temp
Co-authored-by: Pascal admin@serveurperso.com
Website:
- https://llama.app
macOS/iOS:
- macOS Apple Silicon (arm64)
- macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED
- macOS Intel (x64)
- iOS XCFramework
Linux:
- Ubuntu x64 (CPU)
- Ubuntu arm64 (CPU)
- Ubuntu s390x (CPU)
- Ubuntu x64 (Vulkan)
- Ubuntu arm64 (Vulkan)
- Ubuntu x64 (ROCm 7.14)
- Ubuntu x64 (OpenVINO)
- Ubuntu x64 (SYCL FP32)
- Ubuntu x64 (SYCL FP16)
Android:
- Android arm64 (CPU)
Windows:
- Windows x64 (CPU)
- Windows arm64 (CPU)
- Windows arm64 (OpenCL Adreno)
- Windows x64 (CUDA 12) - CUDA 12.4 DLLs
- Windows x64 (CUDA 13) - CUDA 13.3 DLLs
- Windows arm64 (CUDA 13) (preview) - CUDA 13.4 DLLs
- Windows x64 (Vulkan)
- Windows x64 (OpenVINO)
- Windows x64 (SYCL)
- Windows x64 (ROCm 7.14)
openEuler:
- DISABLED
- openEuler x86 (310p)
- openEuler x86 (910b, ACL Graph)
- openEuler aarch64 (310p)
- openEuler aarch64 (910b, ACL Graph)
UI:
- UI

opencl: transpose the K tile in local memory for FA prefill kernels (#26428)
Website:
- https://llama.app
macOS/iOS:
- macOS Apple Silicon (arm64)
- macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED
- macOS Intel (x64)
- iOS XCFramework
Linux:
- Ubuntu x64 (CPU)
- Ubuntu arm64 (CPU)
- Ubuntu s390x (CPU)
- Ubuntu x64 (Vulkan)
- Ubuntu arm64 (Vulkan)
- Ubuntu x64 (ROCm 7.14)
- Ubuntu x64 (OpenVINO)
- Ubuntu x64 (SYCL FP32)
- Ubuntu x64 (SYCL FP16)
Android:
- Android arm64 (CPU)
Windows:
- Windows x64 (CPU)
- Windows arm64 (CPU)
- Windows arm64 (OpenCL Adreno)
- Windows x64 (CUDA 12) - CUDA 12.4 DLLs
- Windows x64 (CUDA 13) - CUDA 13.3 DLLs
- Windows arm64 (CUDA 13) (preview) - CUDA 13.4 DLLs
- Windows x64 (Vulkan)
- Windows x64 (OpenVINO)
- Windows x64 (SYCL)
- Windows x64 (ROCm 7.14)
openEuler:
- DISABLED
- openEuler x86 (310p)
- openEuler x86 (910b, ACL Graph)
- openEuler aarch64 (310p)
- openEuler aarch64 (910b, ACL Graph)
UI:
- UI

ggml-cpu : fix missing Q5_0 dispatch in SpaceMiT backend (#26792)
Website:
- https://llama.app
macOS/iOS:
- macOS Apple Silicon (arm64)
- macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED
- macOS Intel (x64)
- iOS XCFramework
Linux:
- Ubuntu x64 (CPU)
- Ubuntu arm64 (CPU)
- Ubuntu s390x (CPU)
- Ubuntu x64 (Vulkan)
- Ubuntu arm64 (Vulkan)
- Ubuntu x64 (ROCm 7.2)
- Ubuntu x64 (OpenVINO)
- Ubuntu x64 (SYCL FP32)
- Ubuntu x64 (SYCL FP16)
Android:
- Android arm64 (CPU)
Windows:
- Windows x64 (CPU)
- Windows arm64 (CPU)
- Windows arm64 (OpenCL Adreno)
- Windows x64 (CUDA 12) - CUDA 12.4 DLLs
- Windows x64 (CUDA 13) - CUDA 13.3 DLLs
- Windows x64 (Vulkan)
- Windows x64 (OpenVINO)
- Windows x64 (SYCL)
- Windows x64 (HIP)
openEuler:
- DISABLED
- openEuler x86 (310p)
- openEuler x86 (910b, ACL Graph)
- openEuler aarch64 (310p)
- openEuler aarch64 (910b, ACL Graph)
UI:
- UI

server: report the isolate working directory from get_info (#26773)
- server: report the isolate working directory from get_info
Without an explicit cwd, get_info fell back to the server process
working directory even when a tools runtime was configured. That named a
host path no tool would ever run in, since an isolate starts in a
directory of its own.
It now asks the isolate for its working directory in that case, and
keeps the process one only when the tools run on the host.
- remove redundant comment
Co-authored-by: Xuan-Son Nguyen thichthat@gmail.com
Website:
- https://llama.app
macOS/iOS:
- macOS Apple Silicon (arm64)
- macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED
- macOS Intel (x64)
- iOS XCFramework
Linux:
- Ubuntu x64 (CPU)
- Ubuntu arm64 (CPU)
- Ubuntu s390x (CPU)
- Ubuntu x64 (Vulkan)
- Ubuntu arm64 (Vulkan)
- Ubuntu x64 (ROCm 7.2)
- Ubuntu x64 (OpenVINO)
- Ubuntu x64 (SYCL FP32)
- Ubuntu x64 (SYCL FP16)
Android:
- Android arm64 (CPU)
Windows:
- Windows x64 (CPU)
- Windows arm64 (CPU)
- Windows arm64 (OpenCL Adreno)
- Windows x64 (CUDA 12) - CUDA 12.4 DLLs
- Windows x64 (CUDA 13) - CUDA 13.3 DLLs
- Windows x64 (Vulkan)
- Windows x64 (OpenVINO)
- Windows x64 (SYCL)
- Windows x64 (HIP)
openEuler:
- DISABLED
- openEuler x86 (310p)
- openEuler x86 (910b, ACL Graph)
- openEuler aarch64 (310p)
- openEuler aarch64 (910b, ACL Graph)
UI:
- UI

tts: account for the vocoder pass in the timings line (#26733)
get_output runs the waveform work the pipeline defers to it, from a
single trailing window to a full pass depending on the model. Measuring
it keeps the reported total and the audio to process ratio honest.
Website:
- https://llama.app
macOS/iOS:
- macOS Apple Silicon (arm64)
- macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED
- macOS Intel (x64)
- iOS XCFramework
Linux:
- Ubuntu x64 (CPU)
- Ubuntu arm64 (CPU)
- Ubuntu s390x (CPU)
- Ubuntu x64 (Vulkan)
- Ubuntu arm64 (Vulkan)
- Ubuntu x64 (ROCm 7.2)
- Ubuntu x64 (OpenVINO)
- Ubuntu x64 (SYCL FP32)
- Ubuntu x64 (SYCL FP16)
Android:
- Android arm64 (CPU)
Windows:
- Windows x64 (CPU)
- Windows arm64 (CPU)
- Windows arm64 (OpenCL Adreno)
- Windows x64 (CUDA 12) - CUDA 12.4 DLLs
- Windows x64 (CUDA 13) - CUDA 13.3 DLLs
- Windows x64 (Vulkan)
- Windows x64 (OpenVINO)
- Windows x64 (SYCL)
- Windows x64 (HIP)
openEuler:
- DISABLED
- openEuler x86 (310p)
- openEuler x86 (910b, ACL Graph)
- openEuler aarch64 (310p)
- openEuler aarch64 (910b, ACL Graph)
UI:
- UI

metal : avoid threadgroup matrix array instantiation in kernel_lightning_indexer (#26646)
- In MSL, declaring an array of matrix types like threadgroup half4x4 causes
a 'no matching constructor' compilation error because MSL matrix types do not
have zero-argument default constructors and threadgroup variables cannot have
initializers.
- Fix this by declaring a POD threadgroup half array instead and casting
to threadgroup half4x4 * for matrix indexing.
Signed-off-by: JamePeng jame_peng@sina.com
Website:
- https://llama.app
macOS/iOS:
- macOS Apple Silicon (arm64)
- macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED
- macOS Intel (x64)
- iOS XCFramework
Linux:
- Ubuntu x64 (CPU)
- Ubuntu arm64 (CPU)
- Ubuntu s390x (CPU)
- Ubuntu x64 (Vulkan)
- Ubuntu arm64 (Vulkan)
- Ubuntu x64 (ROCm 7.2)
- Ubuntu x64 (OpenVINO)
- Ubuntu x64 (SYCL FP32)
- Ubuntu x64 (SYCL FP16)
Android:
- Android arm64 (CPU)
Windows:
- Windows x64 (CPU)
- Windows arm64 (CPU)
- Windows arm64 (OpenCL Adreno)
- Windows x64 (CUDA 12) - CUDA 12.4 DLLs
- Windows x64 (CUDA 13) - CUDA 13.3 DLLs
- Windows x64 (Vulkan)
- Windows x64 (OpenVINO)
- Windows x64 (SYCL)
- Windows x64 (HIP)
openEuler:
- DISABLED
- openEuler x86 (310p)
- openEuler x86 (910b, ACL Graph)
- openEuler aarch64 (310p)
- openEuler aarch64 (910b, ACL Graph)
UI:
- UI

ci : onboard AMD ROCm CI with gfx1151 fixes (#26544)
- ci: prepare for amd rocm ci
Signed-off-by: Aaron Teo aaron.teo1@ibm.com
- ci: fix editorconfig-checker
Signed-off-by: Aaron Teo aaron.teo1@ibm.com
- ci: fix device not recognised
Signed-off-by: Aaron Teo aaron.teo1@ibm.com
- ci: rename gpu-amd to gpu-hip
Signed-off-by: Aaron Teo aaron.teo1@ibm.com
- ci: gpu-hip to gpu-rocm
haha
Signed-off-by: Aaron Teo aaron.teo1@ibm.com
- CUDA: allow integrated-GPU host output buffer in debug assert
On integrated GPUs (APUs), the scheduler can legitimately place a graph
node's output on the host-visible buffer, which ggml_cuda_compute_forward
already handles. The debug assert in ggml_cuda_graph_evaluate_and_capture
required every node output to be on the device buffer, so a debug build
aborts on such a node (e.g. attn_residual ADD -> ROCm_Host on RDNA3.5).
The source-tensor assert directly below already permits this via the
integrated + cuda_host exception; apply the same exception to the node's
own output buffer. Debug-only; no effect on release/compute.
Fixes test-recurrent-state-rollback on gfx1151 (Strix Halo).
- ci: enable unified memory for ROCm gfx1151 job
Work around a coherence issue on integrated RDNA3.5 (gfx1151) where GPU
kernels reading mmap-loaded weights can return incorrect output, which
makes test-llama-archs (and real inference) intermittently wrong.
GGML_CUDA_ENABLE_UNIFIED_MEMORY=1 uses managed memory, which restores
coherence. Remove once the underlying ROCm/HIP issue is fixed.
- test-llama-archs: skip jamba on HIP backend
jamba produces incorrect output (~0.55 NMSE vs CPU) on the HIP backend on
RDNA3.5 (gfx1151); the SSM kernels need separate investigation. Skip it
for now, matching the existing per-backend carve-outs (WebGPU), so the
ROCm CI can run the test for the remaining architectures.
- ci: use HIP_LAUNCH_BLOCKING for ROCm gfx1151 job
The gfx1151 ROCm CI job produced incorrect inference output (qwen3 perplexity ~88 vs ~9.4) due to an async-execution correctness issue in the HIP path. Serializing kernel launches with HIP_LAUNCH_BLOCKING=1 restores correctness. This replaces the earlier GGML_CUDA_ENABLE_UNIFIED_MEMORY workaround, which did not fix batched inference.
- test-backend-sampler: skip top-k subtests on HIP backend
The ROCm backend does not support the TOP_K/ARGSORT op at vocab scale (no CUB; bitonic argsort is capped at ncols <= 1024), so top-k/top-p backend samplers cannot be offloaded. The penalties, set_sampler, mixed, and top_p subtests assert that offload happened, so they fail on HIP. Skip them until TOP_K is supported on the ROCm backend.
- Update tests/test-backend-sampler.cpp
Co-authored-by: Aaron Teo taronaeo@gmail.com
- Update tests/test-backend-sampler.cpp
Co-authored-by: Georgi Gerganov ggerganov@gmail.com
Signed-off-by: Aaron Teo aaron.teo1@ibm.com
Co-authored-by: Aaron Teo aaron.teo1@ibm.com
Co-authored-by: Jim Wu ywu@xilinx.com
Co-authored-by: Aaron Teo taronaeo@gmail.com
Co-authored-by: Georgi Gerganov ggerganov@gmail.com
Website:
- https://llama.app
macOS/iOS:
- macOS Apple Silicon (arm64)
- macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED
- macOS Intel (x64)
- iOS XCFramework
Linux:
- Ubuntu x64 (CPU)
- Ubuntu arm64 (CPU)
- Ubuntu s390x (CPU)
- Ubuntu x64 (Vulkan)
- Ubuntu arm64 (Vulkan)
- Ubuntu x64 (ROCm 7.2)
- Ubuntu x64 (OpenVINO)
- Ubuntu x64 (SYCL FP32)
- Ubuntu x64 (SYCL FP16)
Android:
- Android arm64 (CPU)
Windows:
- Windows x64 (CPU)
- Windows arm64 (CPU)
- Windows arm64 (OpenCL Adreno)
- Windows x64 (CUDA 12) - CUDA 12.4 DLLs
- Windows x64 (CUDA 13) - CUDA 13.3 DLLs
- Windows x64 (Vulkan)
- Windows x64 (OpenVINO)
- Windows x64 (SYCL)
- Windows x64 (HIP)
openEuler:
- DISABLED
- openEuler x86 (310p)
- openEuler x86 (910b, ACL Graph)
- openEuler aarch64 (310p)
- openEuler aarch64 (910b, ACL Graph)
UI:
- UI

build : remove GGML_METAL_USE_BF16 from all build scripts (#26604)
Website:
- https://llama.app
macOS/iOS:
- macOS Apple Silicon (arm64)
- macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED
- macOS Intel (x64)
- iOS XCFramework
Linux:
- Ubuntu x64 (CPU)
- Ubuntu arm64 (CPU)
- Ubuntu s390x (CPU)
- Ubuntu x64 (Vulkan)
- Ubuntu arm64 (Vulkan)
- Ubuntu x64 (ROCm 7.2)
- Ubuntu x64 (OpenVINO)
- Ubuntu x64 (SYCL FP32)
- Ubuntu x64 (SYCL FP16)
Android:
- Android arm64 (CPU)
Windows:
- Windows x64 (CPU)
- Windows arm64 (CPU)
- Windows arm64 (OpenCL Adreno)
- Windows x64 (CUDA 12) - CUDA 12.4 DLLs
- Windows x64 (CUDA 13) - CUDA 13.3 DLLs
- Windows x64 (Vulkan)
- Windows x64 (OpenVINO)
- Windows x64 (SYCL)
- Windows x64 (HIP)
openEuler:
- DISABLED
- openEuler x86 (310p)
- openEuler x86 (910b, ACL Graph)
- openEuler aarch64 (310p)
- openEuler aarch64 (910b, ACL Graph)
UI:
- UI

metal: implement DSv4 Lightning Indexer (#25893)
- metal: implement F16 Lightning Indexer
- Implement GGML_OP_LIGHTNING_INDEXER for 128-dimensional, 64-head inputs
with F32 queries and weights plus F16 keys and masks.
- Add tiled and tail kernels and test KV lengths around 8- and 64-element
boundaries.
llama-bench (--mmap 1, -fa 1, -p 512, -n 128; d=0/10k/20k/30k):
Before:
- pp512: 153.73 ± 0.87 t/s
- tg128: 8.91 ± 0.04 t/s
- pp512 @ d10000: 73.90 ± 0.39 t/s
- tg128 @ d10000: 8.66 ± 0.03 t/s
- pp512 @ d20000: 45.83 ± 0.18 t/s
- tg128 @ d20000: 8.26 ± 0.03 t/s
- pp512 @ d30000: 33.40 ± 0.21 t/s
- tg128 @ d30000: 7.94 ± 0.01 t/s
After:
- pp512: 155.19 ± 0.91 t/s
- tg128: 8.95 ± 0.04 t/s
- pp512 @ d10000: 86.95 ± 0.69 t/s
- tg128 @ d10000: 9.00 ± 0.05 t/s
- pp512 @ d20000: 62.01 ± 0.45 t/s
- tg128 @ d20000: 8.68 ± 0.04 t/s
- pp512 @ d30000: 49.18 ± 0.33 t/s
- tg128 @ d30000: 8.60 ± 0.02 t/s
Assisted-by: Codex
- metal: stage Lightning Indexer K tiles
- Stage and dequantize K in F16 threadgroup memory before simdgroup matrix loads.
- Zero-fill partial tiles and guard stores so all KV segments use the same numerical path.
- Support F32, F16, BF16, Q4_0, Q4_1, Q5_0, Q5_1, and Q8_0 K caches.
llama-bench (--mmap 1, -fa on, -p 512, -n 128; d=0/10k/20k):
- pp512: 160.38 +/- 1.01 t/s
- tg128: 9.08 +/- 0.03 t/s
- pp512 @ d10000: 88.37 +/- 0.46 t/s
- tg128 @ d10000: 9.07 +/- 0.04 t/s
- pp512 @ d20000: 62.53 +/- 0.46 t/s
- tg128 @ d20000: 8.84 +/- 0.03 t/s
Assisted-by: Codex
- dedup Lightning Indexer constants, fix flaky test
- cont : fix whitespace
Co-authored-by: forforever73 690105611@qq.com
Co-authored-by: Georgi Gerganov ggerganov@gmail.com
Website:
- https://llama.app
macOS/iOS:
- macOS Apple Silicon (arm64)
- macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED
- macOS Intel (x64)
- iOS XCFramework
Linux:
- Ubuntu x64 (CPU)
- Ubuntu arm64 (CPU)
- Ubuntu s390x (CPU)
- Ubuntu x64 (Vulkan)
- Ubuntu arm64 (Vulkan)
- Ubuntu x64 (ROCm 7.2)
- Ubuntu x64 (OpenVINO)
- Ubuntu x64 (SYCL FP32)
- Ubuntu x64 (SYCL FP16)
Android:
- Android arm64 (CPU)
Windows:
- Windows x64 (CPU)
- Windows arm64 (CPU)
- Windows arm64 (OpenCL Adreno)
- Windows x64 (CUDA 12) - CUDA 12.4 DLLs
- Windows x64 (CUDA 13) - CUDA 13.3 DLLs
- Windows x64 (Vulkan)
- Windows x64 (OpenVINO)
- Windows x64 (SYCL)
- Windows x64 (HIP)
openEuler:
- DISABLED
- openEuler x86 (310p)
- openEuler x86 (910b, ACL Graph)
- openEuler aarch64 (310p)
- openEuler aarch64 (910b, ACL Graph)
UI:
- UI

test: fix some CI errors (#26415)
Website:
- https://llama.app
macOS/iOS:
- macOS Apple Silicon (arm64)
- macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED
- macOS Intel (x64)
- iOS XCFramework
Linux:
- Ubuntu x64 (CPU)
- Ubuntu arm64 (CPU)
- Ubuntu s390x (CPU)
- Ubuntu x64 (Vulkan)
- Ubuntu arm64 (Vulkan)
- Ubuntu x64 (ROCm 7.2)
- Ubuntu x64 (OpenVINO)
- Ubuntu x64 (SYCL FP32)
- Ubuntu x64 (SYCL FP16)
Android:
- Android arm64 (CPU)
Windows:
- Windows x64 (CPU)
- Windows arm64 (CPU)
- Windows arm64 (OpenCL Adreno)
- Windows x64 (CUDA 12) - CUDA 12.4 DLLs
- Windows x64 (CUDA 13) - CUDA 13.3 DLLs
- Windows x64 (Vulkan)
- Windows x64 (OpenVINO)
- Windows x64 (SYCL)
- Windows x64 (HIP)
openEuler:
- DISABLED
- openEuler x86 (310p)
- openEuler x86 (910b, ACL Graph)
- openEuler aarch64 (310p)
- openEuler aarch64 (910b, ACL Graph)
UI:
- UI

vulkan: add POOL_1D op (#25431)
- vulkan : add pool1d push constants and pipeline field
Declared data structures needed for POOL1D OP, which are the vk_op_pool1d_push_constants struct and pipeline_pool1d_f32 field.
- vulkan : add pool1d compute shader
Added pool1d.comp for Vulkan backend mirroring the existing pool2d shader.
- vulkan : add full GGML_OP_POOL_1D support
Added pipeline creation and op dispatch for 1D pooling in the Vulkan backend.
- vulkan : fix pool1d shader logic
Registered pool1d_f32 in vulkan-shaders-gen.cpp and fixed tensor dimension indices and avg pool scale.
- vulkan : fix pool1d end boundary crash and expand test coverage
Fixed an issue where the shader crashed when the end boundary was negative when k0 < p0. Also, added more test cases related to this fix.
Website:
- https://llama.app
macOS/iOS:
- macOS Apple Silicon (arm64)
- macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED
- macOS Intel (x64)
- iOS XCFramework
Linux:
- Ubuntu x64 (CPU)
- Ubuntu arm64 (CPU)
- Ubuntu s390x (CPU)
- Ubuntu x64 (Vulkan)
- Ubuntu arm64 (Vulkan)
- Ubuntu x64 (ROCm 7.2)
- Ubuntu x64 (OpenVINO)
- Ubuntu x64 (SYCL FP32)
- Ubuntu x64 (SYCL FP16)
Android:
- Android arm64 (CPU)
Windows:
- Windows x64 (CPU)
- Windows arm64 (CPU)
- Windows arm64 (OpenCL Adreno)
- Windows x64 (CUDA 12) - CUDA 12.4 DLLs
- Windows x64 (CUDA 13) - CUDA 13.3 DLLs
- Windows x64 (Vulkan)
- Windows x64 (OpenVINO)
- Windows x64 (SYCL)
- Windows x64 (HIP)
openEuler:
- DISABLED
- openEuler x86 (310p)
- openEuler x86 (910b, ACL Graph)
- openEuler aarch64 (310p)
- openEuler aarch64 (910b, ACL Graph)
UI:
- UI

server: support inp embd to generate next token (#26313)
- server: support embd for sampled token
- fix ~server_batch()
Website:
- https://llama.app
macOS/iOS:
- macOS Apple Silicon (arm64)
- macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED
- macOS Intel (x64)
- iOS XCFramework
Linux:
- Ubuntu x64 (CPU)
- Ubuntu arm64 (CPU)
- Ubuntu s390x (CPU)
- Ubuntu x64 (Vulkan)
- Ubuntu arm64 (Vulkan)
- Ubuntu x64 (ROCm 7.2)
- Ubuntu x64 (OpenVINO)
- Ubuntu x64 (SYCL FP32)
- Ubuntu x64 (SYCL FP16)
Android:
- Android arm64 (CPU)
Windows:
- Windows x64 (CPU)
- Windows arm64 (CPU)
- Windows arm64 (OpenCL Adreno)
- Windows x64 (CUDA 12) - CUDA 12.4 DLLs
- Windows x64 (CUDA 13) - CUDA 13.3 DLLs
- Windows x64 (Vulkan)
- Windows x64 (OpenVINO)
- Windows x64 (SYCL)
- Windows x64 (HIP)
openEuler:
- DISABLED
- openEuler x86 (310p)
- openEuler x86 (910b, ACL Graph)
- openEuler aarch64 (310p)
- openEuler aarch64 (910b, ACL Graph)
UI:
- UI

model: Add Laguna-S-2.1 LLM_TYPE (#26233)
Website:
- https://llama.app
macOS/iOS:
- macOS Apple Silicon (arm64)
- macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED
- macOS Intel (x64)
- iOS XCFramework
Linux:
- Ubuntu x64 (CPU)
- Ubuntu arm64 (CPU)
- Ubuntu s390x (CPU)
- Ubuntu x64 (Vulkan)
- Ubuntu arm64 (Vulkan)
- Ubuntu x64 (ROCm 7.2)
- Ubuntu x64 (OpenVINO)
- Ubuntu x64 (SYCL FP32)
- Ubuntu x64 (SYCL FP16)
Android:
- Android arm64 (CPU)
Windows:
- Windows x64 (CPU)
- Windows arm64 (CPU)
- Windows arm64 (OpenCL Adreno)
- Windows x64 (CUDA 12) - CUDA 12.4 DLLs
- Windows x64 (CUDA 13) - CUDA 13.3 DLLs
- Windows x64 (Vulkan)
- Windows x64 (OpenVINO)
- Windows x64 (SYCL)
- Windows x64 (HIP)
openEuler:
- DISABLED
- openEuler x86 (310p)
- openEuler x86 (910b, ACL Graph)
- openEuler aarch64 (310p)
- openEuler aarch64 (910b, ACL Graph)
UI:
- UI

mtmd: support MiMo-V2.5 audio input (RVQ-based model) (#26190)
- gguf converter for mimo audio
- fix conv
- cpp impl
- nits
- nits 2
Website:
- https://llama.app
macOS/iOS:
- macOS Apple Silicon (arm64)
- macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED
- macOS Intel (x64)
- iOS XCFramework
Linux:
- Ubuntu x64 (CPU)
- Ubuntu arm64 (CPU)
- Ubuntu s390x (CPU)
- Ubuntu x64 (Vulkan)
- Ubuntu arm64 (Vulkan)
- Ubuntu x64 (ROCm 7.2)
- Ubuntu x64 (OpenVINO)
- Ubuntu x64 (SYCL FP32)
- Ubuntu x64 (SYCL FP16)
Android:
- Android arm64 (CPU)
Windows:
- Windows x64 (CPU)
- Windows arm64 (CPU)
- Windows arm64 (OpenCL Adreno)
- Windows x64 (CUDA 12) - CUDA 12.4 DLLs
- Windows x64 (CUDA 13) - CUDA 13.3 DLLs
- Windows x64 (Vulkan)
- Windows x64 (OpenVINO)
- Windows x64 (SYCL)
- Windows x64 (HIP)
openEuler:
- DISABLED
- openEuler x86 (310p)
- openEuler x86 (910b, ACL Graph)
- openEuler aarch64 (310p)
- openEuler aarch64 (910b, ACL Graph)
UI:
- UI

server + ui: fix stream routes for model names containing a slash (#26137)
- server + ui: refactor resumable stream routes to query string conv_id
The conversation id can embed a model name containing slashes
(ggml-org/...) in router mode, which the decoded path splits before the
:conv_id param is captured, so stop and resume never matched the
session. Move the id to the conv_id query string on the public routes
and on the internal router -> child hop, where slashes survive
encoding. Handlers are unchanged since query and path params land in
the same map. Add a regression test with a slashed model name.
- server: move stream route docs to server-stream.h
Address review: ngxson wants the main server.cpp registration code kept
clean and simple, with route-level explanations living in the header.
Move the query string rationale and the lookup ownership note next to
the handler declarations in server-stream.h, and shorten the wiring
comment to a pointer.
- server: cancel a pending request when its stream is stopped during model load
The conversation was registered in the conv map only after the blocking
autoload wait, so a stop issued while the model loaded found nothing to
cancel and the request went on to generate an orphan once the load
ended. Register the conversation before the wait and give the entry a
ticket: a stop erases the entry, and the parked request checks its
ticket after the wait and aborts with 400 instead of starting. A newer
request on the same conversation replaces the entry, so only the
stopped request is cancelled. Add a regression test that stops during
the load window.
- server + ui: resume a stream after a page reload during model load
A pending request died with the client socket when the page was
reloaded while its model was loading, so no session ever existed and
the conversation had nothing to recover. A session request that waited
for a load now detaches from the client socket and reaches the child
regardless, the session buffer receives the generation, and the resume
route answers 503 while the owner is loading so the client retries
instead of dropping its state. The WebUI persists the pending stream at
send time, quietly polls on 503, and attaches once the session exists.
Add a regression test that drops the client during the load window.
- ui: show the model load progress again after a page refresh
The resume wait was invisible, so a conversation refreshed while its
model was loading showed nothing until the first byte. On a 503 from
the resume probe, mark the conversation as loading again so the
assistant row persisted at send time renders the processing info, and
target the model frozen in the persisted stream state for the
progress, since the row has no model yet and the dropdown may not be
restored.
- fix CI
- fix CI bis
Website:
- https://llama.app
macOS/iOS:
- macOS Apple Silicon (arm64)
- macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED
- macOS Intel (x64)
- iOS XCFramework
Linux:
- Ubuntu x64 (CPU)
- Ubuntu arm64 (CPU)
- Ubuntu s390x (CPU)
- Ubuntu x64 (Vulkan)
- Ubuntu arm64 (Vulkan)
- Ubuntu x64 (ROCm 7.2)
- Ubuntu x64 (OpenVINO)
- Ubuntu x64 (SYCL FP32)
- Ubuntu x64 (SYCL FP16)
Android:
- Android arm64 (CPU)
Windows:
- Windows x64 (CPU)
- Windows arm64 (CPU)
- Windows arm64 (OpenCL Adreno)
- Windows x64 (CUDA 12) - CUDA 12.4 DLLs
- Windows x64 (CUDA 13) - CUDA 13.3 DLLs
- Windows x64 (Vulkan)
- Windows x64 (OpenVINO)
- Windows x64 (SYCL)
- Windows x64 (HIP)
openEuler:
- DISABLED
- openEuler x86 (310p)
- openEuler x86 (910b, ACL Graph)
- openEuler aarch64 (310p)
- openEuler aarch64 (910b, ACL Graph)
UI:
- UI

hexagon: fix Windows crash when op_poll is enabled (#26029)
Website:
- https://llama.app
macOS/iOS:
- macOS Apple Silicon (arm64)
- macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED
- macOS Intel (x64)
- iOS XCFramework
Linux:
- Ubuntu x64 (CPU)
- Ubuntu arm64 (CPU)
- Ubuntu s390x (CPU)
- Ubuntu x64 (Vulkan)
- Ubuntu arm64 (Vulkan)
- Ubuntu x64 (ROCm 7.2)
- Ubuntu x64 (OpenVINO)
- Ubuntu x64 (SYCL FP32)
- Ubuntu x64 (SYCL FP16)
Android:
- Android arm64 (CPU)
Windows:
- Windows x64 (CPU)
- Windows arm64 (CPU)
- Windows arm64 (OpenCL Adreno)
- Windows x64 (CUDA 12) - CUDA 12.4 DLLs
- Windows x64 (CUDA 13) - CUDA 13.3 DLLs
- Windows x64 (Vulkan)
- Windows x64 (OpenVINO)
- Windows x64 (SYCL)
- Windows x64 (HIP)
openEuler:
- DISABLED
- openEuler x86 (310p)
- openEuler x86 (910b, ACL Graph)
- openEuler aarch64 (310p)
- openEuler aarch64 (910b, ACL Graph)
UI:
- UI

metal : add f16 type support to leaky relu (#25981)
Website:
- https://llama.app
macOS/iOS:
- macOS Apple Silicon (arm64)
- macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED
- macOS Intel (x64)
- iOS XCFramework
Linux:
- Ubuntu x64 (CPU)
- Ubuntu arm64 (CPU)
- Ubuntu s390x (CPU)
- Ubuntu x64 (Vulkan)
- Ubuntu arm64 (Vulkan)
- Ubuntu x64 (ROCm 7.2)
- Ubuntu x64 (OpenVINO)
- Ubuntu x64 (SYCL FP32)
- Ubuntu x64 (SYCL FP16)
Android:
- Android arm64 (CPU)
Windows:
- Windows x64 (CPU)
- Windows arm64 (CPU)
- Windows arm64 (OpenCL Adreno)
- Windows x64 (CUDA 12) - CUDA 12.4 DLLs
- Windows x64 (CUDA 13) - CUDA 13.3 DLLs
- Windows x64 (Vulkan)
- Windows x64 (OpenVINO)
- Windows x64 (SYCL)
- Windows x64 (HIP)
openEuler:
- DISABLED
- openEuler x86 (310p)
- openEuler x86 (910b, ACL Graph)
- openEuler aarch64 (310p)
- openEuler aarch64 (910b, ACL Graph)
UI:
- UI

ggml: enable PowerPC backend variants on AIX (#25983)
- ggml: enable PowerPC backend variants on AIX
Allow the PowerPC CPU backend variants to be built on AIX by extending the platform check in the CMake configuration. This reuses the existing PowerPC backend implementations without changing their behavior.
Also fix a missing semicolon in the PowerPC Q0 matmul implementation.
- Fix missing semicolon in sgemm.cpp
Website:
- https://llama.app
macOS/iOS:
- macOS Apple Silicon (arm64)
- macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED
- macOS Intel (x64)
- iOS XCFramework
Linux:
- Ubuntu x64 (CPU)
- Ubuntu arm64 (CPU)
- Ubuntu s390x (CPU)
- Ubuntu x64 (Vulkan)
- Ubuntu arm64 (Vulkan)
- Ubuntu x64 (ROCm 7.2)
- Ubuntu x64 (OpenVINO)
- Ubuntu x64 (SYCL FP32)
- Ubuntu x64 (SYCL FP16)
Android:
- Android arm64 (CPU)
Windows:
- Windows x64 (CPU)
- Windows arm64 (CPU)
- Windows arm64 (OpenCL Adreno)
- Windows x64 (CUDA 12) - CUDA 12.4 DLLs
- Windows x64 (CUDA 13) - CUDA 13.3 DLLs
- Windows x64 (Vulkan)
- Windows x64 (OpenVINO)
- Windows x64 (SYCL)
- Windows x64 (HIP)
openEuler:
- DISABLED
- openEuler x86 (310p)
- openEuler x86 (910b, ACL Graph)
- openEuler aarch64 (310p)
- openEuler aarch64 (910b, ACL Graph)
UI:
- UI

common: resolve draft repo to its requested sidecar (#25955)
With -hfd pointing to a repo shipping speculative sidecars, the draft
resolved to the main model of that repo, since find_best_model()
excludes sidecar files, and the explicit draft plan suppressed the
sidecar discovery on the -hf repo.
The draft plan already discovers its sidecars, they were just never
consumed. Wire them as the draft, following the fallback pattern of
the main plan, so this now works as expected:
llama-server -hf repo -hfd repo --spec-type draft-dflash
Website:
- https://llama.app
macOS/iOS:
- macOS Apple Silicon (arm64)
- macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED
- macOS Intel (x64)
- iOS XCFramework
Linux:
- Ubuntu x64 (CPU)
- Ubuntu arm64 (CPU)
- Ubuntu s390x (CPU)
- Ubuntu x64 (Vulkan)
- Ubuntu arm64 (Vulkan)
- Ubuntu x64 (ROCm 7.2)
- Ubuntu x64 (OpenVINO)
- Ubuntu x64 (SYCL FP32)
- Ubuntu x64 (SYCL FP16)
Android:
- Android arm64 (CPU)
Windows:
- Windows x64 (CPU)
- Windows arm64 (CPU)
- Windows arm64 (OpenCL Adreno)
- Windows x64 (CUDA 12) - CUDA 12.4 DLLs
- Windows x64 (CUDA 13) - CUDA 13.3 DLLs
- Windows x64 (Vulkan)
- Windows x64 (OpenVINO)
- Windows x64 (SYCL)
- Windows x64 (HIP)
openEuler:
- DISABLED
- openEuler x86 (310p)
- openEuler x86 (910b, ACL Graph)
- openEuler aarch64 (310p)
- openEuler aarch64 (910b, ACL Graph)
UI:
- UI

hexagon: add CLAMP op (#25934)
Website:
- https://llama.app
macOS/iOS:
- macOS Apple Silicon (arm64)
- macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED
- macOS Intel (x64)
- iOS XCFramework
Linux:
- Ubuntu x64 (CPU)
- Ubuntu arm64 (CPU)
- Ubuntu s390x (CPU)
- Ubuntu x64 (Vulkan)
- Ubuntu arm64 (Vulkan)
- Ubuntu x64 (ROCm 7.2)
- Ubuntu x64 (OpenVINO)
- Ubuntu x64 (SYCL FP32)
- Ubuntu x64 (SYCL FP16)
Android:
- Android arm64 (CPU)
Windows:
- Windows x64 (CPU)
- Windows arm64 (CPU)
- Windows arm64 (OpenCL Adreno)
- Windows x64 (CUDA 12) - CUDA 12.4 DLLs
- Windows x64 (CUDA 13) - CUDA 13.3 DLLs
- Windows x64 (Vulkan)
- Windows x64 (OpenVINO)
- Windows x64 (SYCL)
- Windows x64 (HIP)
openEuler:
- DISABLED
- openEuler x86 (310p)
- openEuler x86 (910b, ACL Graph)
- openEuler aarch64 (310p)
- openEuler aarch64 (910b, ACL Graph)
UI:
- UI

model: rotate injected K/V cache for DFlash (#25823)
- dflash: rotate injected K/V cache when using K/V quantization
- Update src/models/dflash.cpp
Co-authored-by: Georgi Gerganov ggerganov@gmail.com
- clearer format
- remove trailing whitespace
Co-authored-by: Georgi Gerganov ggerganov@gmail.com
Website:
- https://llama.app
macOS/iOS:
- macOS Apple Silicon (arm64)
- macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED
- macOS Intel (x64)
- iOS XCFramework
Linux:
- Ubuntu x64 (CPU)
- Ubuntu arm64 (CPU)
- Ubuntu s390x (CPU)
- Ubuntu x64 (Vulkan)
- Ubuntu arm64 (Vulkan)
- Ubuntu x64 (ROCm 7.2)
- Ubuntu x64 (OpenVINO)
- Ubuntu x64 (SYCL FP32)
- Ubuntu x64 (SYCL FP16)
Android:
- Android arm64 (CPU)
Windows:
- Windows x64 (CPU)
- Windows arm64 (CPU)
- Windows arm64 (OpenCL Adreno)
- Windows x64 (CUDA 12) - CUDA 12.4 DLLs
- Windows x64 (CUDA 13) - CUDA 13.3 DLLs
- Windows x64 (Vulkan)
- Windows x64 (OpenVINO)
- Windows x64 (SYCL)
- Windows x64 (HIP)
openEuler:
- DISABLED
- openEuler x86 (310p)
- openEuler x86 (910b, ACL Graph)
- openEuler aarch64 (310p)
- openEuler aarch64 (910b, ACL Graph)
UI:
- UI

opencl: load and use kernel_gemm_moe_q6_k_f32_ns from bin kernel lib (#25797)
Website:
- https://llama.app
macOS/iOS:
- macOS Apple Silicon (arm64)
- macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED
- macOS Intel (x64)
- iOS XCFramework
Linux:
- Ubuntu x64 (CPU)
- Ubuntu arm64 (CPU)
- Ubuntu s390x (CPU)
- Ubuntu x64 (Vulkan)
- Ubuntu arm64 (Vulkan)
- Ubuntu x64 (ROCm 7.2)
- Ubuntu x64 (OpenVINO)
- Ubuntu x64 (SYCL FP32)
- Ubuntu x64 (SYCL FP16)
Android:
- Android arm64 (CPU)
Windows:
- Windows x64 (CPU)
- Windows arm64 (CPU)
- Windows arm64 (OpenCL Adreno)
- Windows x64 (CUDA 12) - CUDA 12.4 DLLs
- Windows x64 (CUDA 13) - CUDA 13.3 DLLs
- Windows x64 (Vulkan)
- Windows x64 (OpenVINO)
- Windows x64 (SYCL)
- Windows x64 (HIP)
openEuler:
- DISABLED
- openEuler x86 (310p)
- openEuler x86 (910b, ACL Graph)
- openEuler aarch64 (310p)
- openEuler aarch64 (910b, ACL Graph)
UI:
- UI

docs: added a note about using OpenCl with Adreno 810 (#25786)
Website:
- https://llama.app
macOS/iOS:
- macOS Apple Silicon (arm64)
- macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED
- macOS Intel (x64)
- iOS XCFramework
Linux:
- Ubuntu x64 (CPU)
- Ubuntu arm64 (CPU)
- Ubuntu s390x (CPU)
- Ubuntu x64 (Vulkan)
- Ubuntu arm64 (Vulkan)
- Ubuntu x64 (ROCm 7.2)
- Ubuntu x64 (OpenVINO)
- Ubuntu x64 (SYCL FP32)
- Ubuntu x64 (SYCL FP16)
Android:
- Android arm64 (CPU)
Windows:
- Windows x64 (CPU)
- Windows arm64 (CPU)
- Windows arm64 (OpenCL Adreno)
- Windows x64 (CUDA 12) - CUDA 12.4 DLLs
- Windows x64 (CUDA 13) - CUDA 13.3 DLLs
- Windows x64 (Vulkan)
- Windows x64 (OpenVINO)
- Windows x64 (SYCL)
- Windows x64 (HIP)
openEuler:
- DISABLED
- openEuler x86 (310p)
- openEuler x86 (910b, ACL Graph)
- openEuler aarch64 (310p)
- openEuler aarch64 (910b, ACL Graph)
UI:
- UI

opencl: do not use clCreateBufferWithProperties when targeting CL 2.x (#25673)
macOS/iOS:
- macOS Apple Silicon (arm64)
- macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED
- macOS Intel (x64)
- iOS XCFramework
Linux:
- Ubuntu x64 (CPU)
- Ubuntu arm64 (CPU)
- Ubuntu s390x (CPU)
- Ubuntu x64 (Vulkan)
- Ubuntu arm64 (Vulkan)
- Ubuntu x64 (ROCm 7.2)
- Ubuntu x64 (OpenVINO)
- Ubuntu x64 (SYCL FP32)
- Ubuntu x64 (SYCL FP16)
Android:
- Android arm64 (CPU)
Windows:
- Windows x64 (CPU)
- Windows arm64 (CPU)
- Windows arm64 (OpenCL Adreno)
- Windows x64 (CUDA 12) - CUDA 12.4 DLLs
- Windows x64 (CUDA 13) - CUDA 13.3 DLLs
- Windows x64 (Vulkan)
- Windows x64 (OpenVINO)
- Windows x64 (SYCL)
- Windows x64 (HIP)
openEuler:
- DISABLED
- openEuler x86 (310p)
- openEuler x86 (910b, ACL Graph)
- openEuler aarch64 (310p)
- openEuler aarch64 (910b, ACL Graph)
UI:
- UI