Search: “models”

mtmd: support Qwen3-TTS (note: breaking change to llama-tts binary) (#26254) convert text model main model load ok convert encoder ok speaker encoder loading ok speaker enc graph adapt vocab for backb

GitHub’s context-aware secret classifier improves detection quality, raises weighted acceptance by 11.5%, and reduces median scan execution time by 86%. The post GitHub’s model for secret detection: F

Model-Saver: Write the SWA pattern, 15 more architectures roundtrip (#29042) llama: read the SWA pattern as a period or a per-layer array Add llama_model_base::load_swa_pattern(), which reads sliding_

src : add n_expert_used_max function (#28323) src : add n_expert_used_max function With Commit c61b98b ('model: add NVIDIA Nemotron-3-Puzzle-75B-A9B (NemotronHPuzzle) support (#25444)') it is now poss

tests : 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

Overview New version has been released. Nightly build: b10566 Web UI: the nightly-tag.txt asset contains the tag of the corresponding nightly release More info: dist : releases and versioning of ggml-

What's Changed Improved Gemma 4 tool calling and multi-turn reasoning, including more reliable tool-response continuations Fixed a recurrent MLX model cache leak that could increase memory use across

What's Changed llama: update llama.cpp to b11521 for decision models and EmbeddingGemma 2 by @jmorganca in #18917 server: reuse verified manifests and loaded models in inference routes by @dhiltgen in

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

models: pad on the left with ggml_pad_ext (#29567) models: pad on the left with ggml_pad_ext The Parakeet, LFM2-Audio, Granite Speech and Gemma 4 audio encoders build a left padding as a right pad fol

server : allow RANK pooling batch splitting for causal LLM rerankers (ie. Qwen3 and Qwen3-VL) (#28876) server : allow splitting RANK pooling for causal LLM rerankers Rerank models fall into two catego

What's Changed GET /api/show now advertises each model's thinking controls and default: curl http://localhost:11434/api/show -d '{'model': 'glm-5.3-flash:cloud'}' { 'thinking': { 'values': ['low', 'hi

metal: fix NaN in mul_mm_id when activations exceed f16 range (#26223) test-backend-ops: reproduce MUL_MAT_ID NaN for activations beyond f16 The Metal mul_mm_id path narrows src1 to half for the simdg

models: clean up some dead switch branches in old models (#28669) Some of these if statements were copypastaed in a former refactor and never cleaned up to remove the cases that could never happen any

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

common: fix explicit -md precedence over draft sidecar resolution (#26165) common: fix explicit -md precedence over draft sidecar resolution Follow-up of #25955, an explicit --model-draft file given w

model: load YaRN beta metadata for laguna models (#30331) Assisted-by: Codex Co-authored-by: Adam Caldwell accaldwell@users.noreply.github.com Website: https://llama.app Attestations: https://github.c

model: fix vllm d3 multi seq case (#30408) model: fix vllm d3 multi seq case add TODO Website: https://llama.app Attestations: https://github.com/ggml-org/llama.cpp/attestations/55219202 macOS/iOS: ma

model : support MiniCPM-V 4.7 (#29416) mtmd : add MiniCPM-V 4.7 support Signed-off-by: tc-mb tianchi_cai@icloud.com model : allow mrope time from an extra position slot Signed-off-by: tc-mb tianchi_ca

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

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

model: support nimble decision model (#29844) Website: https://llama.app Attestations: https://github.com/ggml-org/llama.cpp/attestations/52332773 macOS/iOS: macOS Apple Silicon (arm64) macOS Apple Si

model: add support for clef decision model (text-only) (#29831) init support for clef (text only) more static graph clean up nits nits 2 Update gguf-py/gguf/constants.py Co-authored-by: Sigbjørn Skjær

What's Changed server: fix intermittent 'model not found' errors. by @rick-github in #18438 server: apply structured outputs in a single pass on thinking models by @jessegross in #18479 app: avoid Sys

server : allow model downloads at model limit fix issue #26809 (#28530) Website: https://llama.app Attestations: https://github.com/ggml-org/llama.cpp/attestations/47055500 macOS/iOS: macOS Apple Sili

[Model] Support for Spark2_5ForCausalLM implementation (#27868) Add Spark3 Model rename spark3 -> spark2_5 Co-authored-by: Sigbjørn Skjæret sigbjorn.skjaeret@huggingface.co Co-authored-by: dongjiang d

models : fix GDN normalization from max to rsqrt (#28068) models: use flash-linear-attention's l2norm for gated delta net q/k The GDN q/k normalization is defined by flash-linear-attention as l2norm(x

model: correctly support input vision for deepseek4 (#28154) model: correctly support input vision for deepseek4 nits Website: https://llama.app Attestations: https://github.com/ggml-org/llama.cpp/att

model: add DSpark support for Nemotron3.5 (#27804) model: add DSpark support for Nemotron3.5 Update src/models/dflash.cpp Co-authored-by: Sigbjørn Skjæret sigbjorn.skjaeret@huggingface.co Co-authored-

llama: model_loader: add TENSOR_READ_LAZY (#27794) llama: model_loader: add TENSOR_GET_ROW_LAZY add --tensor-read-lazy rename to TENSOR_READ_LAZY gen docs address comments Website: https://llama.app A

mtmd: use pillow-accurate algo, correct resize_algo for all models (#27594) mtmd: use pillow-accurate resize algo, correct resize_algo for all models speed optimization Website: https://llama.app Atte

server: (router) lazy-load startup_models after main setup (#27424) server: (router) lazy-load startup_models after main setup only allow is_first_load to populate it nits nits 2 Website: https://llam

model: use ggml_rope_set_offset() (#27382) model: use ggml_rope_set_offset() partially apply to deepseek2 Website: https://llama.app Attestations: https://github.com/ggml-org/llama.cpp/attestations/42

llama : MTP support for DeepSeek V3.2 (#26457) llama : MTP support for DeepSeek V3.2 model : no need to include MTP layers during DeepSeek V3.2 model type discovery Co-authored-by: Stanisław Szymczyk

metal: fix memory unwire if model is freed without any GPU operations (#26082) metal: fix memory leak if model is freed without any GPU operations metal: run dummy work only if residency sets are used

model: add NextN/MTP speculative decoding support for GLM_DSA (GLM-5.2) (#25980) model: add NextN/MTP speculative decoding support for GLM_DSA (GLM-5.2) Adds GLM-5.2 NextN/MTP as a --spec-type draft-m

model: Add support for Nanbeige4.2 (#25994) support nanbeige4.2 model fix fix flake8 Lint check fix loop bound check and drop redundant head_dim Co-authored-by: root lizongqiang@kanzhun.com Website: h

Ollama v0.30.4 is a patch release addressing a bug in the llama-server component related to incorrect parameter wiring in the Gemma 4 model implementation. This fix ensures Gemma 4 models operate corr

<channel|>This release update for `local-ai` (version v0.20.5-rc1) expands model compatibility by integrating several popular large language models. It allows users to run models such as Kimi-K2.5,...

graph: skip the LM head for pooled embeddings (#30445) graph: skip the LM head for pooled embeddings A context that extracts pooled embeddings outputs one vector per sequence, but every model still ex

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

TP: fix split state and granularity for fused QKV gemma4, qwen35 (#28965) model: calculate split states for attn_qkv from n_head * n_embd_head_k required for gemma4 with --fuse-qkv, where n_embd is 53

Use Ollama models in ChatGPT Desktop Ollama models can now be used directly in ChatGPT Desktop, so you can keep your existing workflow while running open models. Setup is available from the Ollama app

OpenVINO: Update OV to 2026.3.1, whisper.cpp support, Qwen3.5 on NPU, and new ops (#27843) OpenVINO Backend: Fuse IM2COL + MatMul convolution into OpenVINO convolution ci:ggml-ov: Skip recurrent state

DeepseekV4: fix rollback with multi-seq (#26756) DeepseekV4: fix rollback with multi-seq fix model loading make pending rollback single use only clear cache for seq_id for full load add assert for com

fit: also take into account n_streams (#27496) fit: also take into account n_streams server: make the draft context follow the target context With a non-unified KV cache the target context now holds n