Të kërkuara: Të dhënat u përditësuan më 27 tetor 2026

Kategoritë

Internet1356
Komunikim321
Audio dhe video898
Grafikë dhe dizajn539
Zyrë dhe produktivitet1124
Mjete zhvillimi3134
Mjete IA529
Siguri dhe privatësi385
Mjete sistemi3114
Lojëra523
Arsim dhe shkencë239
Rrjet dhe IT284

Shkarko llama.cpp b9893

LLM inference in C/C++

Ky është një version i vjetër. Versioni i fundit është b9994. llama.cpp b9994 · Publikuar:

Skedarët e instalimit b9893

ArkitekturaLlojiShtrirjaMadhësia e skedaritShkarkimiSHA256
64-bit ZIP → Portativ — — github.com VirusTotal

Lidhja dhe SHA256 vijnë nga manifesti i komunitetit të Windows Package Manager. Krahasoni hash-in e skedarit të shkarkuar para se ta ekzekutoni.

Shënimet e versionit

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

https://github.com/ggml-org/llama.cpp/releases/tag/b9893

Etiketat

Ndaje