Skip to content

v0.4.2 Preview

Pre-release
Pre-release

Choose a tag to compare

View all tags
@github-actions github-actions released this 29 Jul 05:08
preview-v0.4.2
4a834dd

Warning

Rolling preview build from v0.4.2 at 4a834dd7aae8. Assets and moving Docker tags are replaced by newer successful branch builds. Last updated: 29/07/2026 05:01.

Changelog
  • Updated the llama.cpp base through upstream commit 6ba5ef247. Notable inherited changes include MiniMax-M3 sparse attention and vision, GLM-5.2-Vision and its indexer, Laguna, Nanbeige4.2, MiMo-V2.5 audio, DeepSeek4 fused operators, BitNet conversion, gpt-oss EAGLE3-v3, server MCP stdio, "reasoning_effort": "none", multi-end-sequence reasoning budgets, draft-sidecar discovery, broad backend and Web UI updates, and the unified --load-mode (-lm) selector. GGML_OP_COUNT is now 105 and the RPC protocol version is 4.0.5.
  • Enabled bounded-memory native KVarN attention on portable-only CUDA devices, including the pre-Turing route needed by issue #112. A versioned backend capability record now distinguishes portable body-plus-F16/BF16-tail support from specialized MMA, split/vector decode, original-V support, and per-route query limits. Portable CUDA prompt batches consume rotated compressed records directly instead of re-entering classic full-score attention; Turing-and-newer route selection is unchanged. CI compiles explicit CUDA 12.4 Maxwell/Pascal/Volta targets and CUDA 13.1 current targets, while pre-Turing runtime qualification remains pending matching hardware.
  • Added experimental --split-mode tensor support for standard quantized and KVarN caches with F16/BF16 precision tails. Cache components split only at complete-head boundaries, dynamic meta graphs and auxiliary speculative contexts follow the target topology safely, invalid weights fail during model creation, and invalid cache layouts fail during context creation. Layer split is unchanged; physical multi-GPU peer transfer, NCCL, and heterogeneous rollback still require validation.
  • Added CUDA support for serialized ternary, group-64 Q2_0 model weights across dequantization, GET_ROWS, MMVQ, and MMQ, including corrected template declarations. This remains distinct from Bee's cache-facing GGML_TYPE_Q2_0S.
  • Fixed CUDA matrix-kernel selection for padded or offset right-hand-side tensors. MMVF, MMF, fused, and expert paths now reject addresses or strides that are unsafe for their float2 loads instead of asserting in the kernel.
  • Fixed KVarN correctness during unaligned eager stores, multi-turn suffix removal, compact-tail reprocessing, and deep SWA rollback. Reopened groups retain the correct F16 source, compressed-body tails avoid unnecessary reprocessing, and record-safe rollback boundaries prevent stale rows.
  • Restored context creation for cacheless, noncausal architectures after KV-tail type resolution; requesting a precision tail for a model without cache memory now fails explicitly.
  • Fixed release and test infrastructure: Windows CPU and Vulkan jobs resolve Visual Studio through vswhere, CPU packages require OpenMP, release ccache can seed from the nearest ancestor version branch, LLAMA_BUILD_TESTS=ON builds compile after the upstream reasoning-budget API change, and release regressions run without ignored local files.

macOS:

Linux:

Windows:

Docker:

  • CPU: docker pull ghcr.io/anbeeld/beellama.cpp:server-cpu-preview-v0.4.2
  • CUDA: docker pull ghcr.io/anbeeld/beellama.cpp:server-cuda-preview-v0.4.2
  • CUDA 12: docker pull ghcr.io/anbeeld/beellama.cpp:server-cuda12-preview-v0.4.2
  • CUDA 13: docker pull ghcr.io/anbeeld/beellama.cpp:server-cuda13-preview-v0.4.2
  • ROCm: docker pull ghcr.io/anbeeld/beellama.cpp:server-rocm-preview-v0.4.2
  • Vulkan: docker pull ghcr.io/anbeeld/beellama.cpp:server-vulkan-preview-v0.4.2
  • SYCL: docker pull ghcr.io/anbeeld/beellama.cpp:server-sycl-preview-v0.4.2

Browse all container images

Assets 19
Loading