b11307
llama : 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
Knowledge catalogue
llama : 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
model : 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
model : 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
test-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
sampling : 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
opencl: 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-
CUDA/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
What'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
model : 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
metal : 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
vulkan: 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
model : support Gemma4 DSpark draft backbone (#29226) dspark: add Gemma 4 draft support Add GGUF conversion and runtime support for full-attention and SWA Gemma 4 DSpark drafts, including tied output
server: Add support for binding to multiple addresses (#28690) Add support for binding llama-server to multiple addresses Assisted-by: Codex remove redundant thread handler make it clear about overlap
CUDA: replace GGML_FA_ALL_QUANTS with GGML_FA_QUANTS, more control over what is compiled (#28079) CUDA: add configurable FA quant combinations Assisted-by: Codex remove all flags but , add runtime fal
vulkan: FA MMQ should use fp32 for Q quantization calculations (#27413) Codex found that qd could be a denorm and 1/qd would overflow. Website: https://llama.app Attestations: https://github.com/ggml-
Muse 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
add 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
metal: implement DSv4 Lightning Indexer (#25893) metal: implement F16 Lightning Indexer Implement GGML_OP_LIGHTNING_INDEXER for 128-dimensional, 64-head inputs with F32 queries and weights plus F16 ke
vulkan: 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
OpenVINO: 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
rpc: avoid serializing buffers from other servers (#26500) rpc: avoid serializing buffers from other servers Only include remote buffer pointers when the buffer belongs to the RPC dispatcher receiving
Muse 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
chat : 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
metal: 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
What'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