دا یوه زړه نسخه ده. اوسنۍ نسخه b9994 ده. llama.cpp b9994 · د خپرېدو نېټه:
د نصب فایلونه b8261
| جوړښت | ډول | د نصب ساحه | د فایل اندازه | ډاونلوډ | SHA256 |
|---|---|---|---|---|---|
| 64-bit | ZIP → پورټېبل | — | — | github.com | VirusTotal |
لینک او SHA256 د Windows Package Manager د ټولنې له مانیفسټ څخه اخیستل شوي. د ډاونلوډ شوي فایل له چلولو مخکې یې هش پرتله کړئ.
د خپرونې یادښتونه
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)