github Anbeeld/beellama.cpp preview-v0.4.3
v0.4.3 Preview

pre-release5 hours ago

Warning

Rolling preview build from v0.4.3 at 9d59db2e3e99. Assets and moving Docker tags are replaced by newer successful branch builds. Last updated: 29/07/2026 16:00.

Changelog
  • Fixed HIP/ROCm KVarN caches incorrectly falling back to full F16 materialization when precision tails were enabled. KVarN now honors the backend's dedicated native-tail capability before consulting generic segmented-tail support, avoiding context-sized fallback allocations on supported AMD GPUs while leaving ordinary HIP segmented-tail routing unchanged.

macOS:

Linux:

Windows:

Docker:

  • CPU: docker pull ghcr.io/anbeeld/beellama.cpp:server-cpu-preview-v0.4.3
  • CUDA: docker pull ghcr.io/anbeeld/beellama.cpp:server-cuda-preview-v0.4.3
  • CUDA 12: docker pull ghcr.io/anbeeld/beellama.cpp:server-cuda12-preview-v0.4.3
  • CUDA 13: docker pull ghcr.io/anbeeld/beellama.cpp:server-cuda13-preview-v0.4.3
  • ROCm: docker pull ghcr.io/anbeeld/beellama.cpp:server-rocm-preview-v0.4.3
  • Vulkan: docker pull ghcr.io/anbeeld/beellama.cpp:server-vulkan-preview-v0.4.3
  • SYCL: docker pull ghcr.io/anbeeld/beellama.cpp:server-sycl-preview-v0.4.3

Browse all container images

Don't miss a new beellama.cpp release

NewReleases is sending notifications on new releases.