Priljubljeno: Podatki posodobljeni: 27. oktober 2026

Kategorije

Internet1356
Komunikacija321
Zvok in video898
Grafika in oblikovanje539
Pisarna in produktivnost1124
Orodja za razvijalce3134
Orodja UI529
Varnost in zasebnost385
Sistemska orodja3114
Igre523
Izobraževanje in znanost239
Omrežje in IT284

llama.cpp b8417: prenos za Windows

LLM inference in C/C++

To je starejša različica. Najnovejša različica je b9994. llama.cpp b9994 · Izdano:

Namestitvene datoteke b8417

ArhitekturaVrstaZa kogaVelikost datotekePrenesiSHA256
64-bitno ZIP → Prenosna različica — — github.com VirusTotal

Povezava in SHA256 izhajata iz manifesta skupnosti Windows Package Manager. Pred zagonom primerjajte zgoščeno vrednost prenesene datoteke.

Opombe ob izdaji

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

Oznake

Deli