Il s’agit d’une ancienne version. La dernière version est la b9994. llama.cpp b9994 · Date de sortie:
Fichiers d’installation b7502
| Architecture | Type | Portée | Taille du fichier | Télécharger | SHA256 |
|---|---|---|---|---|---|
| 64 bits | ZIP → Portable | — | — | github.com | VirusTotal |
Le lien et l’empreinte SHA256 proviennent du manifeste communautaire du Gestionnaire de paquets Windows. Comparez l’empreinte du fichier téléchargé avant de l’exécuter.
Notes de version
vulkan: Implement set_tensor_async and the event interfaces (#18047)
The goal is to enable the async loading code paths in
llama_model_loader::load_all_data, originally from #7896. This works and the
loads themselves are faster, but with host visible vidmem I think the cost of
allocating/mapping vidmem moves and becomes more expensive, and I don't see a
benefit by default. But with GGML_VK_DISABLE_HOST_VISIBLE_VIDMEM=1 I do see a
significant improvement in model loading time.
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) - 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)
- openEuler aarch64 (310p)
- openEuler aarch64 (910b)