CompanyAnthropic8 recent entries11 Aug 2026v0.32.8Muse Glimmer Muse Glimmer is now available on all platforms. Muse Glimmer can power coding agent applications such as Claude Code, Codex, Pi and more, as well as long-running personal assistants such →11 Sept 2026b10905CUDA/HIP: Flash Attention tuning (gfx1201) (#28102) HIP: enable mma FA for head size 256 on RDNA4, tune configs Assisted-by: Claude Assisted-by: Codex HIP: prefer whole-tile FA grids over stream-k on →15 Sept 2026b10981OpenVINO: optimize stateful decode and GPU MoE inference (#28638) exclude GPU/NPU failing POOL_2D case Fix pool case ggml-openvino: fix stateful decode for Gemma-4 per-layer-type head sizes ggml-openv
CompanyOpenAI6 recent entries14 Jul 2026v0.32.0What's Changed New interactive agent experience: running ollama now launches an agent to help you code and delegate work ❯ ollama Ollama 0.32.0 ▸ Chat, Code, & Work (glm-5.2:cloud) Chat with models, c→4 Sept 2026b10813opencl: add Adreno xmem SDPA path (#26331) opencl: add Adreno xmem SDPA path Assisted-by: Codex Removed the Adreno-specific queue profiling override Clean up formatting 修复数值误差优化gqa/mask attn Assisted-→23 Sept 2026b11126vulkan: add IQ4_XS MMQ/MMV matmul kernels (#28415) vulkan: optimize IQ4_XS matmul kernels Assisted-by: OpenAI Codex vulkan: address IQ4_XS review nits drop the dead LOAD_VEC_A != 8 branch in the IQ4_X→24 Sept 2026b11160vulkan: int8 coopmat1 matmul implementation for AMD RDNA3 and RDNA4 (#27952) vulkan: add int8 coopmat quantized matmul shader apply scales inline use scalar sums probe and directly access coopmat valu→2 Oct 2026b11334metal : release temporary private transfer buffers (#29777) metal : release temporary private transfer buffers Assisted-by: OpenAI Codex metal : fix order and formatting Co-authored-by: Niklas Wenzel →7 Oct 2026b11472sampling : use greedy selection for eligible temperature-zero chains (#29797) sampling : use greedy selection for eligible temperature-zero chains Assisted-by: OpenAI Codex Apply suggestion from @gger
CompanyMeta8 recent entries30 Sept 2026b11279add GLM-5.3-Flash (GLM5-Next) support (#27773) Rebase GLM-Next support onto master, and migrate to llama-memory-hybrid-idx Add initial MTP support Merge branch optimizations. Reduce allocated compute →1 Oct 2026b11307llama : preserve original batch order for speculative decoding layer inputs (#29019) llama: preserve original batch order for layer inputs Assisted-by: Codex tests: cover layer-input order across KV l→2 Oct 2026b11334metal : release temporary private transfer buffers (#29777) metal : release temporary private transfer buffers Assisted-by: OpenAI Codex metal : fix order and formatting Co-authored-by: Niklas Wenzel →6 Oct 2026b11454model : add K2 Horizon dense and MoVA support (#29535) model: K2 Horizon gguf conversion code model: loading hparams and tensors in k2-horizon.cpp model: K2 Horizon compute graph model: K2 Horizon com→6 Oct 2026b11438test-llama-archs : initialize backends before generating models (#30034) With GGML_BACKEND_DL=ON, backends must be loaded explicitly before creating models. Assisted-by: Codex Website: https://llama.a→7 Oct 2026b11472sampling : use greedy selection for eligible temperature-zero chains (#29797) sampling : use greedy selection for eligible temperature-zero chains Assisted-by: OpenAI Codex Apply suggestion from @gger→8 Oct 2026b11512model : fix DFlash output head sharing (#30111) llama : fix DFlash output head sharing Assisted-by: Codex dflash : read tied output weights from GGUF metadata Assisted-by: Codex llama : share tied wor→9 Oct 2026b11532model : use exact GELU for ModernBERT encoders (#30108) model : use exact GELU for ModernBERT encoders Assisted-by: Codex model : keep tanh GELU aliases on ggml_geglu Assisted-by: Claude Opus 5.5 mode
CompanyMistral1 recent entries14 Jul 2026v0.32.0What's Changed New interactive agent experience: running ollama now launches an agent to help you code and delegate work ❯ ollama Ollama 0.32.0 ▸ Chat, Code, & Work (glm-5.2:cloud) Chat with models, c
CompanyDeepSeek3 recent entries14 Jul 2026v0.32.0What's Changed New interactive agent experience: running ollama now launches an agent to help you code and delegate work ❯ ollama Ollama 0.32.0 ▸ Chat, Code, & Work (glm-5.2:cloud) Chat with models, c→2 Aug 2026b10232metal: implement DeepSeek V4 hyper-connections (#26459) Implement GGML_OP_DSV4_HC_COMB, GGML_OP_DSV4_HC_PRE, and GGML_OP_DSV4_HC_POST with SIMDgroup register and shuffle optimized kernels. Add Metal d→4 Aug 2026b10254chat : add new template for DeepSeek V4 Flash 0731 (#26398) common/chat: update DeepSeek V4 templates Align the DeepSeek V4 templates with the official encoders while keeping parser behavior out of th
CompanyNVIDIA2 recent entries10 Aug 2026v0.32.7Muse Glimmer Note: Muse Glimmer is currently available via initial support via Ollama's MLX engine on Apple Silicon. Additional support and optimizations for Apple Silicon, NVIDIA, AMD, and other plat→11 Aug 2026v0.32.8Muse Glimmer Muse Glimmer is now available on all platforms. Muse Glimmer can power coding agent applications such as Claude Code, Codex, Pi and more, as well as long-running personal assistants such