追踪 Meta Llama 开源模型和生态工具动态。
test-llama-archs : generate dummy test vocab (#29084) Assisted-by: pi:llama.cpp/DeepSeek-V4-Flash-Vision-Exp **Website:** - **Attestations:** - **macOS/iOS:** - [macOS Apple Silicon (arm64)](https://github.com/ggml-org/llama.cpp/releases/download/b11049/llama-
metal : support qwen4exp hc ops (#29000) Add support for the new DSV4 HC op variants used by qwen4exp: - hc_pre with per-element sigmoid gate (gated variant) - hc_post with identity mixing (comb == nullptr) Assisted-by: pi:llama.cpp/Qwen3.8-27B **Website:** -
cuda : fix CUB argsort corruption caused by in-place keys (#28389) argsort_f32_i32_cuda_cub called the one-shot DeviceRadixSort::SortPairs API with d_keys_in == d_keys_out (temp_keys, temp_keys). CUB's internal double-buffer ping-pong requires distinct key buf
opencl: add support for bin kernel `flash_attn_f32_f16_bin` (#29046) * opencl: add `flash_attn_f32_f16_bin` * opencl: guarded prefill fa **Website:** - **Attestations:** - **macOS/iOS:** - [macOS Apple Silicon (arm64)](https://github.com/ggml-org/llama.cpp/rel
hexagon: add ROLL op support (#29105) **Website:** - **Attestations:** - **macOS/iOS:** - [macOS Apple Silicon (arm64)](https://github.com/ggml-org/llama.cpp/releases/download/b11045/llama-b11045-bin-macos-arm64.tar.gz) - macOS Apple Silicon (arm64, KleidiAI e
hexagon: im2col update (#29103) * ggml-hexagon: accept 1D and padded IM2COL ops * ggml-hexagon: make pure-DDR IM2COL kernel is_2D-aware * ggml-hexagon: extend IM2COL DMA patch-embed fast path to 1D * ggml-hexagon: add blocked-staging general IM2COL DMA kernel
hexagon: HMX flash-attention head_dim padding (support DK=DV=72) (#26539) Allow HMX flash-attention to run with head_dim not a multiple of 64 (e.g. SigLIP head_dim=72), by operating on DK/DV rounded up to 64 with zero-filled tail lanes. **Website:** - **Attest
opencl: add bin kernel `kernel_gemm_noshuffle_q6_k_f32_32b_trans_ila_a8_bin` (#28678) * opencl: add A8 Q6_K non-MoE binary kernel * opencl: fix layout compatibility **Website:** - **Attestations:** - **macOS/iOS:** - [macOS Apple Silicon (arm64)](https://githu
Muse is now available on the Mac, where it can work with your files and apps to take action on your behalf.
ggml : check for allocation failures to prevent crashes (#28149) * ggml : check for allocation failures to prevent crashes * wording **Website:** - **Attestations:** - **macOS/iOS:** - [macOS Apple Silicon (arm64)](https://github.com/ggml-org/llama.cpp/release
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_window_pattern either as one flag per layer or as a period
ggml-webgpu: fix supports_op condition for GET_ROWS (#28978) * fix get_rows vec4 handling * Add src strides checking to vec4_aligned of get_rows and the new test case. **Website:** - **Attestations:** - **macOS/iOS:** - [macOS Apple Silicon (arm64)](https://gi
ggml : handle graph buffer reservation failure (#26070) **Website:** - **Attestations:** - **macOS/iOS:** - [macOS Apple Silicon (arm64)](https://github.com/ggml-org/llama.cpp/releases/download/b11036/llama-b11036-bin-macos-arm64.tar.gz) - macOS Apple Silicon
vulkan: add IQ3_S MMQ matmul kernels (#28822) * vulkan: add IQ3_S MMQ matmul kernels * Make block_a_to_shmem do 2-byte loads (110 bytes is divisible by 2) * Align the check, IQ3_S is also using K tile size **Website:** - **Attestations:** - **macOS/iOS:** - [m
## What's Changed - Added first-run setup when running `ollama`, with options to sign in or continue locally. Setup completion is shared with the desktop app on macOS and Windows. - Added `ollama://apps` to open the desktop app’s Apps page directly on macOS an
llama.cpp build changes resulted in duplicate symbols between libllama and libmtmd. This moves the compat patch into libllama with exported symbols.
## What's Changed * MLX safetensors `ollama create` no longer experimental. GGUF model creation now requires using llama.cpp tooling for safetensor conversion and quantization. * Improved MLX memory handling on Apple Silicon * Runaway repeat token detection no
## What's Changed * gemma4 now supports images and audio on MLX engine * Report cached prompt tokens * Honor GGUF model defined default parameters * MLX, MLX-C, llama.cpp update ## New Contributors * @marcelpetrick made their first contribution in https://gith
Meta returns to the open source ecosystem with the release of Muse Glimmer, a 30B open-weight dense model with a 120K+ context window built for local AI...
## What's Changed * MLX: Qwen3.8 Flash Next support * cmake: make external compat patches idempotent * MLX and llama.cpp update * mlxrunner: add structured output support * mlxrunner: avoid Metal GPU timeouts when loading models from slow storage ## New Contri
### Summary of major features and improvements * Functionally enabled Muse-Glimmer-30B model: * Model card and IR available: [OpenVINO/Muse-Glimmer-30B-int4-ov · Hugging Face](https://huggingface.co/OpenVINO/Muse-Glimmer-30B-int4-ov) * Notebooks to try: * [Mus
# Highlights *710 PRs from 212 contributors.* **New models in this release** (see the [cookbook](https://docs.sglang.io/cookbook) for all supported models): | Model | Type | PRs | Cookbook | |---|---|---|---| | Muse Glimmer | Autoregressive (Multimodal) | [#34
## What's Changed * fix(gemini): remove unsupported $schema from tool parameters by @qbc2016 in https://github.com/agentscope-ai/agentscope/pull/2277 * feat(workspace): share workspace across different agents by @iluv7 in https://github.com/agentscope-ai/agent
## What's Changed * New desktop onboarding flow on first launch * Caches resolved model metadata between requests, cutting time-to-first-token by roughly half (TTFT dropped from ~995 ms to ~524 ms in benchmarks) * Fixes a bug where chat and generate could wedg
## What's Changed * llm: transcode WebP images for llama-server * renderers/qwen: tolerate non-leading system messages **Full Changelog**: https://github.com/ollama/ollama/compare/v0.32.13...v0.32.14
## What's Changed * Fix KSamplerAdvanced with add_noise disabled on nested latents by @kijai in https://github.com/Comfy-Org/ComfyUI/pull/15447 * Update workflow templates to v0.11.40 by @comfyui-wiki in https://github.com/Comfy-Org/ComfyUI/pull/15522 * chore:
# Release v5.15.0 ## New Model additions ### Meta Muse Glimmer Muse Glimmer, released today, is Meta’s new multimodal model, especially designed for agentic use cases. Distilled from Muse to 30B parameters, and released under the Apache 2.0 license, it can be
First v2 release candidate. Pre-releases are opt-in only; `pip install mcp` still resolves to the stable 1.x line. ```bash pip install mcp==2.0.0rc1 # or uv add "mcp==2.0.0rc1" ``` The [documentation](https://py.sdk.modelcontextprotocol.io/v2/) has the full tu
## What's Changed * Add AGENTS.md by @comfyanonymous in https://github.com/Comfy-Org/ComfyUI/pull/14696 * Add some more stuff to AGENTS.md by @comfyanonymous in https://github.com/Comfy-Org/ComfyUI/pull/14704 * Fix Qwen3-VL tokenizer crash with custom embeddin
# vLLM v0.23.0 Release Notes Please note that Minimax M3 is not yet supported in this version. Please follow [vLLM recipe](https://recipes.vllm.ai/MiniMaxAI/MiniMax-M3) for usage guides for M3. ## Highlights This release features 408 commits from 200 contribut
