v0.32.9
NVIDIA Nemotron 3.5 Lightning NVIDIA Nemotron 3.5 Lightning is an open 30B mixture-of-experts (MoE) model with 3B active parameters built for that execution layer of always-on agents. It is designed f
Knowledge catalogue
NVIDIA Nemotron 3.5 Lightning NVIDIA Nemotron 3.5 Lightning is an open 30B mixture-of-experts (MoE) model with 3B active parameters built for that execution layer of always-on agents. It is designed f
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
ggml-cuda: fallback to F32 on device without BF16 hardware acceleration (#28846) ggml-cuda: fallback to F32 on device without BF16 hardware acceleration: (Nvidia >= AMPERE, AMD >= RDNA3 or = CDNA) app
model: add NVIDIA Nemotron-3-Puzzle-75B-A9B (NemotronHPuzzle) support (#25444) hparams: add per-layer n_ff_exp/n_expert_used arrays with scalar-or-array loading G1/G2 infrastructure for variable-per-l
vulkan: support type-aligned GET_ROWS (#28253) vulkan: fall back to CPU for GET_ROWS with misaligned offsets The Vulkan GET_ROWS shader asserts when a tensor's backing-buffer offset plus view_offs is
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
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
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
v0.32.8 is an Oct 10, 2023 release of the ollama repository on GitHub, following a pre‑release tag v0.32.8‑rc0. The update adds Muse Glimmer support for NVIDIA, AMD and additional platforms, with the
v0.22.1-rc1 is a pre-release version of Ollama that includes improvements to MLX sampler batching, tokenizer BPE offset handling, NVIDIA TensorRT Model Optimizer support, and fixes for desktop app sta
llama.cpp release **b8737** is a focused maintenance build that adds missing CUDA error handling to the ggml backend. Specifically, it checks the return values of NVIDIA CUB library calls used in t...
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
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
mtmd: Add Vision Support for Minimax-M3 (#25113) Add preliminary MiniMax-M3 support Text-only port that re-uses existing components: MiniMax-M2 style GQA with per-head QK-norm and partial rotary, Deep
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,
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
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
musa: 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
vulkan: fix missing view-alias dependencies in ggml_vk_graph_optimize (#27812) vulkan: fix missing view-alias dependencies in ggml_vk_graph_optimize is_src_of doesn't treat two views of one tensor as
ggml-cuda : disable MMQ on devices with less than 48 KiB shared memory (#26141) ggml_cuda_should_use_mmq() selects MMQ purely from the quantization type. The current MMQ configurations are designed an
CUDA: Improve NVFP4 W4A4 activation quantization (#25730) Squash history before conflict-resolution during rebase on master WIP commit Add 32-byte loads, restore per-block amax Use nvfp4x4 intrinsic w
The search results do not contain specific information about v0.32.0-rc0. Based on the version numbering and context from Ollama's release patterns, v0.32.0-rc0 is a release candidate for Ollama, a la
B9816 is a release build number for llama.cpp, an open-source project that enables efficient large language model inference in C/C++ on consumer hardware. This release likely contains bug fixes, perfo
v0.30.7-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
v0.30.6-rc0 is a release candidate that fixes kernel template instantiation so library symbols are exported correctly , following improvements from the v0.30 series. The v0.30 base release improved co
Ollama 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
Ollama 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
Ollama 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
b9391 is a build release of llama.cpp, an open-source C/C++ inference framework for running large language models locally. llama.cpp provides lightweight, optimized model inference with support for mu
Based on the release notes available, v0.30.0-rc4 appears to be a release candidate focused on continuous integration and platform-specific optimizations. The title suggests this build targeted Window
Release b8833 of llama.cpp includes updates to the ggml-webgpu backend, fixing compiler warnings and refactoring FlashAttention encoding, along with workflow improvements and precision adjustments for
llama.cpp build **b8751** is a tagged release of the [ggml-org/llama.cpp](https://github.com/ggml-org/llama.cpp) project, a C/C++ library enabling high-performance LLM inference with minimal setup ...