追踪开放权重模型、开源 AI 工具和可复核的仓库更新。
## What's Changed * fix(cli): scope the ACP permission queue to the session by @chiga0 in https://github.com/QwenLM/qwen-code/pull/11802 * feat(channels): add shared output modes with DingTalk support by @qqqys in https://github.com/QwenLM/qwen-code/pull/11822
## What's Changed * docs(serve): record merged ACP boundary acceptance by @wenshao in https://github.com/QwenLM/qwen-code/pull/12024 * fix(ci): wait for the published export renderer before packaging the VSIX by @yiliang114 in https://github.com/QwenLM/qwen-co
Alibaba released the open weights for Qwen3.8-2.4T-A95B (Qwen3.8-Max), its largest open-weight model, bringing near-frontier capabilities to the open...
AI agents on foundation models often misapply healthcare and life sciences decision frameworks, citing the right guideline but applying it incorrectly. This post shares 38 open-source agent skills across 11 HCLS domains that close this gap, with installation s
## Highlights _See the complete change list below._ ## Breaking Changes - fix(core)!: let bash expand project directory variables in command hooks ([#11864](https://github.com/QwenLM/qwen-code/pull/11864)) by @qqqys ## Complete Change List ### Features - feat(
Mozilla’s State of Open Source AI report puts Kimi K3 about four months behind closed frontier models at 30% of the price. <p>Shane has a background in computer engineering and has worked as a freelance consultant in multiple industries. He has a strong affect
## What's Changed * test: record what the Windows inode gates are hiding, and un-skip one by @yiliang114 in https://github.com/QwenLM/qwen-code/pull/11853 * fix(cua): preserve Linux observations and REPL diagnostics by @DragonnZhang in https://github.com/QwenL
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
来源已更新，查看详情及原始发布记录。
Qwen CUA Driver prebuilt binaries (vendored under `packages/cua-driver`). - **macOS**: codesigned + notarized universal binary + `QwenCuaDriver.app` - **Linux**: unsigned (x86_64 + arm64, glibc 2.31 floor) - **Windows**: unsigned UIAccess worker + native SDK p
## What's Changed * test: record what the Windows inode gates are hiding, and un-skip one by @yiliang114 in https://github.com/QwenLM/qwen-code/pull/11853 * fix(cua): preserve Linux observations and REPL diagnostics by @DragonnZhang in https://github.com/QwenL
## Highlights _See the complete change list below._ ## Breaking Changes - Removes configurable message-prefix filtering from channels, so eligible messages now follow normal sender, group, mention, and pairing policies without a prefix. ([#11571](https://githu
## Verify Docker Image Signature All LiteLLM Docker images are signed with [cosign](https://docs.sigstore.dev/cosign/overview/). Every release is signed with the same key introduced in [commit `0112e53`](https://github.com/BerriAI/litellm/commit/0112e53046018d
模型仓库动态。仓库创建：2026-01-30T04:24:21.000Z。最后修改：2026-09-11T11:59:14.000Z。仓库修改不等同于模型正式发布。 数据经第三方 Hugging Face 镜像采集，需以原始模型页面复核。 任务：image-to-text。
# v0.29.0 ## Highlights This release features 594 commits from 277 contributors (91 new)! * **Model Runner V2 is now the default for all models** (#53183), completing the rollout that began with pooling models (#48290). MRV2 also gained CUDA graph memory profi
ONNX Runtime 1.30.0 expands generative AI inference, improves CPU and GPU performance, adds Go bindings, and strengthens runtime reliability. These notes cover changes since ONNX Runtime 1.29.1. ## Highlights - Expanded CUDA inference support with variable-len
# Release v5.17.0 ## New Model additions ### HYV4 Hy4-Preview is a 780B-parameter mixture-of-experts language model that activates 49B parameters per token. Each MoE layer holds 256 routed experts plus one always-active shared expert and routes every token to
模型仓库动态。仓库创建：2026-09-10T02:17:58.000Z。最后修改：2026-09-10T08:18:10.000Z。仓库修改不等同于模型正式发布。 数据经第三方 Hugging Face 镜像采集，需以原始模型页面复核。 任务：image-text-to-text。
来源标注日期：2026-09-10（未提供具体时刻）。 Today, we officially release the DeepSeek-V4.1-Flash model. It is the smallest model in our new architecture family, with native multimodal visual understanding. The new architecture is designed for a higher capability ceiling, fast
模型仓库动态。仓库创建：2026-08-25T06:43:14.000Z。最后修改：2026-09-07T12:13:47.000Z。仓库修改不等同于模型正式发布。 数据经第三方 Hugging Face 镜像采集，需以原始模型页面复核。 任务：image-text-to-text。
# Highlights *786 PRs from 214 contributors.* **New models in this release** (see the [cookbook](https://docs.sglang.io/cookbook) for all supported models): | Model | Type | PRs | Cookbook | |---|---|---|---| | Qwen3.8 (2.4T-A95B) | Autoregressive | [#35758](h
模型仓库动态。仓库创建：2026-08-25T06:45:05.000Z。最后修改：2026-09-04T06:45:54.000Z。仓库修改不等同于模型正式发布。 数据经第三方 Hugging Face 镜像采集，需以原始模型页面复核。 任务：image-text-to-text。
模型仓库动态。仓库创建：2026-08-25T06:42:50.000Z。最后修改：2026-09-04T06:41:23.000Z。仓库修改不等同于模型正式发布。 数据经第三方 Hugging Face 镜像采集，需以原始模型页面复核。 任务：text-generation。
模型仓库动态。仓库创建：2026-08-25T06:43:55.000Z。最后修改：2026-09-04T06:38:42.000Z。仓库修改不等同于模型正式发布。 数据经第三方 Hugging Face 镜像采集，需以原始模型页面复核。 任务：text-generation。
## 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
模型仓库动态。仓库创建：2026-08-27T08:14:27.000Z。最后修改：2026-09-02T06:31:52.000Z。仓库修改不等同于模型正式发布。 数据经第三方 Hugging Face 镜像采集，需以原始模型页面复核。 任务：image-text-to-text。
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...
A vulnerability in huggingface/transformers versions < 5.10.0 allows an attacker to perform arbitrary file writes via path traversal. The issue resides in the `save_pretrained()` methods of `PreTrainedTokenizerBase` and `ProcessorMixin`, where keys from the `c
模型仓库动态。仓库创建：2026-06-16T07:20:33.000Z。最后修改：2026-09-01T11:36:25.000Z。仓库修改不等同于模型正式发布。 数据经第三方 Hugging Face 镜像采集，需以原始模型页面复核。 任务：text-generation。
