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
ToolCursor5 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→4 Sept 2026Project HydraFusion: Frontier quality via multi-model orchestrationIn controlled offline evaluations, HydraFusion’s selective coding workflows matched or exceeded the evaluated Opus 5 baseline while reducing estimated workflow cost. Now available as a research previe→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
ToolOllama8 recent entries29 Sept 2026v0.35.0Decision models Ollama now supports decision models through /v1/systemone, based on TypeSafe’s Jev API. Decision models return choices, probabilities, and scores instead of text. Use them for tasks su→4 Oct 2026v0.40.0-rc1: mlx: match publisher tokenizer semantics (#18779)mlx: match publisher tokenizer semantics Honor pretokenizer stage order, split behavior, Unicode boundaries, added-token normalization, and ranked BPE merges. Handle empty added tokens and empty Metas→4 Oct 2026v0.40.0What's Changed Models run on MLX on Apple Silicon by default In this release, on Apple Silicon devices, model architectures supported by the MLX runtime will automatically run on MLX. ollama pull qwen→6 Oct 2026v0.40.0-rc6: model: add multimodal embeddings (#18820)Implements the EmbeddingGemma2Model architecture on the MLX runner: 24-layer bidirectional text encoder with PLE, shared gemma4 vision/audio towers, mean-pool + L2 output. /api/embed accepts per-item →8 Oct 2026v0.40.2-rc0: server: hide duplicate and downgrade guards from list (#18874)When a legacy GGUF which requires our llama.cpp patch set is loaded, we do a lazy conversion on disk to make it llama.cpp compatible. To support downgrades, we temporarily hold both the new and old GG→8 Oct 2026v0.40.2What's Changed README: add oxi to community integrations by @maziluiosif in #18739 server: hide duplicate and downgrade guards from list by @dhiltgen in #18874 New Contributors @maziluiosif made their→8 Oct 2026v0.40.1What's Changed server: proxy cloud usage and balance APIs by @drifkin in #18829 llama: fix clef head reads past 2GiB on windows by @Gigrise in #18777 cmd: remove account step from CLI onboarding by @h→11 Oct 2026v0.40.3What's Changed ollama launch claude no longer shows a warning about Claude connectors by @hoyyeva in #18878 ollama launch codex no longer warns about service tiers by @hoyyeva in #18879 Paused backgro
ToolVercel AI2 recent entries4 Apr 2026LLM WikiKarpathy’s pattern: LLMs compile raw sources into a persistent interlinked markdown wiki—entity/concept pages, index, log—rather than re-deriving answers from RAG on every query.→19 Sept 2026Inbox triage 2026-09-19Social and low-evidence quarantine moved to raw as rejected. 168 high-specificity articles remain in inbox; four sources were filed.
ToolHugging Face8 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→2 Jun 2026v0.30.1Ollama 0.30 provides improved compatibility and performance using llama.cpp, augments the MLX engine on Apple Silicon for broader hardware support, and brings support for a wider range of models inclu→3 Jun 2026v0.30.4Ollama v0.30.4 is a patch release within the v0.30 series, which offers improved compatibility and performance using llama.cpp, augments the MLX engine on Apple Silicon with wider hardware support, an→3 Jun 2026v0.30.2Ollama v0.30.2 is a patch release from the 0.30 series, which features improved compatibility and performance using llama.cpp, augmented MLX engine support on Apple Silicon, and broader model support →6 Jun 2026v0.30.7-rc1v0.30.7-rc1 is a release candidate for Ollama, an open-source platform for running and managing large language models locally. The v0.30 series represents improved compatibility and performance using →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