Search: “models”

fix(mamba) : make time-step projection input contiguous (#28832) mamba : make time-step projection input contiguous Assisted-by: ChatGPT mamba : skip contiguous copy after normalization Assisted-by: C

Overview This release focuses on backend performance and correctness, broader model coverage, and more robust server/router operation. It adds HRM-Text (DFM Mimir 1B) support, MiMo-V2.6 and HunyuanOCR

server: accept OpenAI video_url content type and data: video URIs (#27921) The OpenAI chat completions API specifies content part type 'video_url' with a {'url': ...} object, and clients typically sen

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

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

server : support typed content (vision/audio/video) input for /v1/embeddings endpoint (#29556) server : support multimodal input for /v1/embeddings (Qwen3-VL-Embedding) Accept the OpenAI-style wrapped

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

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

cuda : warnings cleanup Signed-off-by: Adrien Gallouët angt@huggingface.co Update ggml/src/ggml-cuda/common.cuh Co-authored-by: Sigbjørn Skjæret sigbjorn.skjaeret@huggingface.co Signed-off-by: Adrien

graph : avoid reallocations in the 'no cache' path (#30439) Website: https://llama.app Attestations: https://github.com/ggml-org/llama.cpp/attestations/55354972 macOS/iOS: macOS Apple Silicon (arm64)

ggml-zdnn : introduce Q8_0 mat mul (#29836) ggml-zdnn: initial prototype of q8_0 matmul Signed-off-by: Aaron Teo aaron.teo1@ibm.com docs: update zdnn docs Signed-off-by: Aaron Teo aaron.teo1@ibm.com S

models : remove redundant ggml_cont calls now supported by all unary kernels (#30198) models: remove redundant ggml_cont calls now supported by CUDA unary kernels models: restore cont_2d after sigmoid

hexagon: extend scalar DMA broadcasting support for binary ops (#30245) tests: cover weighted scalar broadcasts Assisted-by: OpenCode ggml : support extended scalar DMA binary ops Assisted-by: OpenCod

webgpu: (Fix CI) fix mul_mat_id with duplicate expert ids (#30451) Fix mm-id of webgpu in the case of ids duplication formatting fix comments to avoid breaking up sentences in comments Website: https:

server : escape the special tokens without std::regex (#30243) The d1-omni and kev prompts escape '<|name|>' in the request text with std::regex_replace. libstdc++ recurses for each char of the name,

chat: replace output string with parts (#30389) chat: replace output string with parts reserve first Website: https://llama.app Attestations: https://github.com/ggml-org/llama.cpp/attestations/5563975

llama.cpp enables LLM inference in C/C++ , and release b9014 represents a build revision or commit snapshot from the llama.cpp repository on GitHub. This release would include bug fixes, feature impro

b9523 is a release build of llama.cpp, an open-source tool for LLM inference in C/C++ that enables language model execution with minimal setup on a wide range of hardware locally and in the cloud. The

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

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

mtmd: support DeepSeek-V4-Flash-Vision-Exp (#28133) mtmd: support DeepSeek-V4-Flash-Vision-Exp handle min/max token counts from CLI rm debugging use GGML_ROPE_TYPE_VISION nits apply review comments co

Overview llama.cpp 0.4.0 adds initial Qwen3.8-Flash-Next and Nemotron-3-Puzzle support, on-demand tensor reading, per-slot server context limits, video input options, and a ggml update to 0.23.0 with

vulkan: add DeepSeek-V4 hyper-connection fused ops (DSV4_HC_COMB/PRE/POST) (#26578) vulkan: add DeepSeek-V4 hyper-connection fused ops (DSV4_HC_COMB/PRE/POST) CUDA has these ops from the DeepSeek-V4 m

chat : split specialized parsers into common/parsers (#27764) chat : split specialized parsers into common/parsers Move the 14 dedicated template parsers out of chat.cpp into one file each under commo

Overview llama.cpp 0.4.1 adds Maple 20B-A1B, Tencent Hy 4, and Spark2.5 support, improves JSON schema handling, chat parsing, logging, and server child-process management, and updates ggml to v0.24.0.

chat : add message delimiters to the DeepSeek V3.2/V4 parser (#29008) chat : add message delimiters to the DeepSeek V3.2/V4 parser Assisted-by: Claude Co-authored-by: Sigbjørn Skjæret sigbjorn.skjaere

cuda: fix sm_70 tile compilation error (#29224) The 5-argument load_ldmatrix added in 1884824 only defines tile<16,8>, so the Volta tile<8,4> does not match. See #29222 for details. Building on 188482

Overview This release focuses on backend performance and correctness, broader model coverage, and more robust server/router operation. It adds HRM-Text (DFM Mimir 1B) support, MiMo-V2.6 and HunyuanOCR

cuda: support Nemotron 3 Puzzle state size 96 for ssm scan (#28717) Website: https://llama.app Attestations: https://github.com/ggml-org/llama.cpp/attestations/50461180 macOS/iOS: macOS Apple Silicon

server : support typed content (vision/audio/video) input for /v1/embeddings endpoint (#29556) server : support multimodal input for /v1/embeddings (Qwen3-VL-Embedding) Accept the OpenAI-style wrapped

vulkan: fix wrong results when a mul_mat reads a slice of a larger cache (#28956) vulkan: read the batch stride of an in place src0 from nb[2] A dim01 contiguous tensor can still be a view whose batch

musa : define CUDA_ARCH for device passes (#29508) The MUSA vendor header never defined CUDA_ARCH, so every architecture test in the shared ggml-cuda sources evaluated to 0. Kernel bodies gated on the

Overview 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

llama: share the nextn tensor flags between models Follow-up of the TODO in glm5-next: move the trunk-only and MTP-only detection that each model copied into a nextn_flags helper of llama_model_base.

vulkan : fix TOP_K for +inf/NaN inputs and k = 1 on negative values (#30107) The bucket search in topk_nary_search.comp started from the range [0, 0xFF800000), which ends just below the ordered-uint m

The no-cache path builds a [n_tokens, n_tokens] mask and passes K and V unpadded, so FLASH_ATTN_EXT sees K->ne[1] == n_tokens. The CUDA kernels for head size 512 require a multiple of FATTN_KQ_STRIDE,