Ommabop: Maʼlumotlar yangilangan sana: 6-noyabr, 2026

Kategoriyalar

Internet1 372
Muloqot323
Audio va video912
Grafika va dizayn549
Ofis va samaradorlik1 134
Dasturchilar uchun vositalar3 173
Sunʼiy intellekt vositalari546
Xavfsizlik va maxfiylik396
Tizim vositalari3 153
Oʻyinlar532
Taʼlim va fan240
Tarmoq va IT289

llama.cpp b8417 yuklab olish

LLM inference in C/C++

Bu eski versiya. Eng soʻnggi versiya: b9994. llama.cpp b9994 · Chiqarilgan sana:

Oʻrnatish fayllari b8417

ArxitekturaTuriQamrovFayl hajmiYuklab olishSHA256
64 bitli ZIP → Portativ — — github.com VirusTotal

Havola va SHA256 Windows paket menejeri (winget) hamjamiyati manifestidan olingan. Ishga tushirishdan oldin yuklab olingan faylning xeshini solishtiring.

Oʻzgarishlar roʻyxati

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)

https://github.com/ggml-org/llama.cpp/releases/tag/b8417

Teglar

Ulashish