Warning
Rolling preview build from v0.4.9 at ea85221ef959. Assets and moving Docker tags are replaced by newer successful branch builds. Last updated: 20/10/2026 00:10.
Changelog
- Updated the llama.cpp base from
c06f84160tofd55cb98f. Inherited changes include multi-GPU MoE caching, LiLiCorr speculative decoding, chat-session APIs, new model support, and backend, server, conversion, and Web UI updates.
macOS:
Linux:
- Ubuntu x64 CPU
- Ubuntu arm64 CPU
- Ubuntu x64 CUDA 12.4
- Ubuntu x64 CUDA 13.3
- Ubuntu x64 Vulkan
- Ubuntu x64 ROCm 7.2
- Ubuntu x64 SYCL
Windows:
- Windows x64 CPU
- Windows x64 Vulkan
- Windows x64 SYCL
- Windows x64 CUDA 12.4 - DLLs
- Windows x64 CUDA 13.3 - DLLs
- Windows x64 HIP
Docker:
- CPU:
docker pull ghcr.io/anbeeld/beellama.cpp:server-cpu-preview-v0.4.9 - CUDA:
docker pull ghcr.io/anbeeld/beellama.cpp:server-cuda-preview-v0.4.9 - CUDA 12:
docker pull ghcr.io/anbeeld/beellama.cpp:server-cuda12-preview-v0.4.9 - CUDA 13.3:
docker pull ghcr.io/anbeeld/beellama.cpp:server-cuda13-preview-v0.4.9 - ROCm:
docker pull ghcr.io/anbeeld/beellama.cpp:server-rocm-preview-v0.4.9 - Vulkan:
docker pull ghcr.io/anbeeld/beellama.cpp:server-vulkan-preview-v0.4.9 - SYCL:
docker pull ghcr.io/anbeeld/beellama.cpp:server-sycl-preview-v0.4.9