Popularno: Podaci ažurirani: 21. studenoga 2026.

Kategorije

Internet1.421
Komunikacija329
Audio i video938
Grafika i dizajn566
Ured i produktivnost1.184
Alati za programere3.288
AI alati610
Sigurnost i privatnost408
Sistemski alati3.194
Igre545
Obrazovanje i znanost242
Mreža i IT294

llama.cpp b7415: preuzimanje za Windows

LLM inference in C/C++

Ovo je starija verzija. Najnovija verzija je b9994. llama.cpp b9994 · Objavljeno:

Instalacijske datoteke b7415

ArhitekturaVrstaZa kogaVeličina datotekePreuzmiSHA256
64-bitno ZIP → Prijenosna verzija — — github.com VirusTotal

Poveznica i SHA256 potječu iz manifesta zajednice Windows Package Manager. Prije pokretanja usporedite hash preuzete datoteke.

Bilješke o izdanju

Warning
Release Format Update: Linux releases will soon use .tar.gz archives instead of .zip. Please make the necessary changes to your deployment scripts.
ggml-hexagon: mm for mtmd (#17894)
- feat: add run_mtmd script for hexagon
- fix: fix issue in fp16xfp32 mm
- fix: remove opt_experiment for fp16xfp32 mm
- fix: ggml-hexagon: matmul fp16xfp32 support non-contigious src0
- fix: fix syntax check for run-mtmd.sh for cli
macOS/iOS:
- macOS Apple Silicon (arm64)
- macOS Intel (x64)
- iOS XCFramework
Linux:
- Ubuntu x64 (CPU)
- Ubuntu x64 (Vulkan)
- Ubuntu s390x (CPU)
Windows:
- Windows x64 (CPU)
- Windows arm64 (CPU)
- Windows x64 (CUDA 12)
- Windows x64 (CUDA 13)
- Windows x64 (Vulkan)
- Windows x64 (SYCL)
- Windows x64 (HIP)
openEuler:
- openEuler x86 (310p)
- openEuler x86 (910b)
- openEuler aarch64 (310p)
- openEuler aarch64 (910b)

https://github.com/ggml-org/llama.cpp/releases/tag/b7415

Oznake

Podijeli