mistralai/Ministral-3-8B-Reasoning-2512 · 仓库更新
模型仓库动态。仓库创建：2025-10-31T08:41:36.000Z。最后修改：2026-07-15T12:22:30.000Z。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。
接入 API · 个人 AI 解读连接自己的模型解读资讯，浏览新闻无需配置。
AI 推理能力
关注大模型推理能力、思考模式、评测与推理技术更新。
48 条资讯按来源发布或更新时间排序
mistralai/Ministral-3-3B-Reasoning-2512 · 仓库更新
模型仓库动态。仓库创建：2025-10-31T08:39:58.000Z。最后修改：2026-07-15T12:21:57.000Z。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。
vLLM 发布: v0.25.0
# vLLM v0.25.0 Release Notes ## Highlights This release features 558 commits from 232 contributors (64 new)! * **Model Runner V2 is now the default for all dense models** (#44443). Building on quantized-model support from the previous release, MRv2 is now the
SGLang 发布: v0.5.15
# Highlights **GLM-5.2 NVFP4, tuned for production**: We took time this cycle to tune GLM-5.2 NVFP4 on Blackwell for optimized production serving. It now runs at **500+ tok/s/user on 8x B300, 450 on 4x GB300** (bs=1). Run GLM-5.2 with our [cookbook](https://do
Transformers 发布: Release v5.13.0
# Release v5.13.0 ## New Model additions ### KimiK 2.5, 2.6, and 2.7 This release includes the architecture for Kimi 2.5 which is used by 2.5-2.7: Kimi K2.5 is an open-source, native multimodal agentic model that advances practical capabilities in long-horizon
Open WebUI 发布: v0.10.2
### Added - 💭 **Streamed reasoning display.** Models that emit thinking or reasoning now show that content as it streams, and it renders correctly in the chat overview and in exported conversations. [Commit](https://github.com/open-webui/open-webui/commit/0b7
vLLM 发布: v0.24.0
# vLLM v0.24.0 Release Notes ## Highlights This release features 571 commits from 256 contributors (77 new)! * **MiniMax-M3**: Added support for the new **MiniMax-M3** model (#45381), with a fast follow-on of BF16/FP8 indexer via MSA (#45892), MXFP4 support (#
Kimi CLI 发布: 1.48.0
## What's Changed * fix(kosong): round-trip empty reasoning content by @RealKai42 in https://github.com/MoonshotAI/kimi-cli/pull/2446 * feat(soul): escalate repeated-tool-call reminders and force-stop on dead-end streak by @jackfish212 in https://github.com/Mo
Gemini Robotics-ER 1.6: Powering real-world robotics tasks through enhanced embodied reasoning
Gemini Robotics ER 1.6: Enhancing spatial reasoning and multi-view understanding for autonomous robotics.
Gemma 4: Byte for byte, the most capable open models
Gemma 4: Our most intelligent open models to date, purpose-built for advanced reasoning and agentic workflows.
Gemini 3 Deep Think: Advancing science, research and engineering
Our most specialized reasoning mode is now updated to solve modern science, research and engineering challenges.
Microsoft AutoGen 发布: python-v0.7.5
## What's Changed * Fix docs dotnet core typo by @lach-g in https://github.com/microsoft/autogen/pull/6950 * Fix loading streaming Bedrock response with tool usage with empty argument by @pawel-dabro in https://github.com/microsoft/autogen/pull/6979 * Support
DeepSeek-V3.1
来源标注日期：2025-08-21（未提供具体时刻）。 Both deepseek-chat and deepseek-reasoner have been upgraded to DeepSeek-V3.1. deepseek-chat corresponds to DeepSeek-V3.1's non-thinking mode, while deepseek-reasoner corresponds to its thinking mode. Key updates in DeepSeek-V3.1: Hy
deepseek-reasoner
来源标注日期：2025-05-28（未提供具体时刻）。 deepseek-reasoner Model Upgraded to DeepSeek-R1-0528: Enhanced Reasoning Capabilities Significant benchmark improvements (Pass@1) AIME 2025: 70.0 → 87.5 (+17.5) GPQA: 71.5 → 81.0 (+9.5) LCB_v6: 63.5 → 73.3 (+9.8) Aider: 57.0 → 71.6
deepseek-chat
来源标注日期：2025-03-24（未提供具体时刻）。 deepseek-chat Model Upgraded to DeepSeek-V3-0324: Enhanced Reasoning Capabilities Significant improvements in benchmark performance: MMLU-Pro: 75.9 → 81.2 (+5.3) GPQA: 59.1 → 68.4 (+9.3) AIME: 39.6 → 59.4 (+19.8) LiveCodeBench: 39.2
deepseek-chat
来源标注日期：2024-12-10（未提供具体时刻）。 The deepseek-chat model has been upgraded to DeepSeek-V2.5-1210, with improvements across various capabilities. Relevant benchmarking results include: Mathematical: Performance on the MATH-500 benchmark has improved from 74.8% to 82
deepseek-chat
来源标注日期：2024-06-28（未提供具体时刻）。 The deepseek-chat model has been upgraded to DeepSeek-V2-0628. Model's reasoning capabilities have improved, as shown in relevant benchmarks: Coding: HumanEval Pass@1 79.88% -> 84.76% Mathematics: MATH ACC@1 55.02% -> 71.02% Reasoni
deepseek-coder
来源标注日期：2024-06-14（未提供具体时刻）。 The deepseek-coder model has been upgraded to DeepSeek-Coder-V2-0614, significantly enhancing its coding capabilities. It has reached the level of GPT-4-Turbo-0409 in code generation, code understanding, code debugging, and code com