Populāri: Dati atjaunināti: 2026. gada 21. novembris

Kategorijas

Internets1421
Saziņa329
Audio un video938
Grafika un dizains566
Birojs un produktivitāte1184
Izstrādes rīki3288
MI rīki610
Drošība un privātums408
Sistēmas rīki3194
Spēles545
Izglītība un zinātne242
Tīkls un IT294

llama.cpp b8179 lejupielādēt

LLM inference in C/C++

Šī ir vecāka versija. Jaunākā versija ir b9994. llama.cpp b9994 · Izlaista:

Instalēšanas faili b8179

ArhitektūraTipsDarbības jomaFaila lielumsLejupielādeSHA256
64 bitu ZIP → Portatīvā — — github.com VirusTotal

Saite un SHA256 ņemti no Windows Package Manager kopienas manifesta. Pirms palaišanas salīdziniet lejupielādētā faila kontrolsummu.

Izmaiņu saraksts

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)

https://github.com/ggml-org/llama.cpp/releases/tag/b8179

Birkas

Kopīgot