ToolClaude Code8 recent entries31 Aug 2026b10715spec : fuse the DFlash encoder into the KV cache injection (#27310) dflash : fuse the encoder into the KV injection decode The encoder is a single fc + norm, but running it as a separate llama_encode →7 Sept 2026b10831vulkan: add TQ1_0 support (mm, mat-vec, mat-vec-id, dequant, get_rows) (#27765) vulkan: add TQ1_0 support (mm, mat-vec, dequant, get_rows) vulkan: pack TQ1_0 powers of 3 into a 32-bit constant Replace→10 Sept 2026b10888vulkan : add command-buffer debug labels for GPU profilers (#28101) vulkan : add command-buffer debug labels for GPU profilers Co-authored-by: gabby-zy z2262718160@gmail.com Assisted-by: Claude Code v
ToolCursor4 recent entries28 Aug 2026b10666tests : run test-save-load-state across all architectures (#27755) tests : run test-save-load-state across all architectures test-save-load-state previously only ran in ctest against a single download→31 Aug 2026b10724kv-cache : optimize restoring non-contiguous cells (#27991) kv cache : batch state restore scatter reads per contiguous run When restoring state into non-contiguous destination cells (e.g. a prompt-ca→6 Oct 2026backup/allozaur-ui-shell-polish: ui : polish the shellThe secondary button gets its own look back and the chat add button its own light surface. Pressable elements get a pointer cursor again, the font rendering smooths on the app shell, the root layout r→12 Oct 2026b11560hexagon: add IM2COL_3D (#30305) hexagon: add IM2COL_3D support Assisted-by: OpenCode hexagon: add DMA paths for IM2COL_3D Assisted-by: OpenCode hexagon: avoid scalar fp16 conversions in IM2COL Assiste
ToolOllama3 recent entries3 Jul 2026b9862B9862 is a continuous build-tagged release from llama.cpp , the open-source C/C++ LLM inference engine. Llama.cpp is the inference engine that powers most of the local-AI ecosystem, including tools li→8 Jul 2026b9909llama.cpp is an open-source software library that performs inference on various large language models , and the project ships continuous build-tagged releases rather than traditional semantic versioni→10 Aug 2026b10342model : Granite-Switch Architecture (#25107) granite-switch: add llama.cpp backend (POC, CPU) New 'granite-switch' architecture: a dense, all-attention Granite-4.1 model with N embedded LoRA adapters
ToolHugging Face4 recent entries10 Apr 2026b8747llama.cpp release **b8747** is the latest build of the C/C++ LLM inference engine, published on April 10, 2026 (commit `fb38d6f`). Its primary change is a bug fix in the `common` layer that resolve...→21 May 2026b9263Release b9263 of llama.cpp includes a merge of HunyuanOCR into HunyuanVL with fixes to OCR vision precision. The update consolidates OCR functionality into the HunyuanVL projector while maintaining co→25 Sept 2026b11178musa: fix PH1 (MTT S5000) operator failures and build issues (#29193) musa: use 16-byte copies for MUSA like sm_70+ ggml_cuda_get_max_cpy_bytes() derives the copy width from CUDA_ARCH. mcc never defin→5 Oct 2026v0.6.0Overview llama.cpp v0.6.0 introduces the new llama_batch_ext extended batch API (with llama_process) for mixed token/embedding inputs and MTP/deepstack state embeddings, adds support for the GLM-5.3-F