Intel OpenVINO 发布: 2026.3.1

来源摘要

### 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: * [Muse Glimmer-30B multimodal reasoning with OpenVINO™](https://openvinotoolkit.github.io/openvino_notebooks/?search=Muse-Glimmer-30B) * [Create VLM-powered Chatbot using OpenVINO Generate API](https://openvinotoolkit.github.io/openvino_notebooks/?search=Muse-Glimmer-30B) * Blogs: * [Running Meta’s Muse Glimmer 30B Locally with OpenVINO™ GenAI](https://medium.com/openvino-toolkit/running-metas-muse-glimmer-30b-locally-with-openvino-genai-756753644b02); * [Day 0 Support for Muse Glimmer from Meta on Intel Platforms](https://www.intel.com/content/www/us/en/developer/articles/community/day-0-local-agentic-ai-with-metas-muse-glimmer.html) * Functionally enabled Qwen3.8-27B model: * Model card and IR available: [OpenVINO/Qwen3.8-27B-int4-ov · Hugging Face](https://huggingface.co/OpenVINO/Qwen3.8-27B-int4-ov/tree/2026.3.1) * Notebook to try: [Create VLM-powered Chatbot using OpenVINO Generate API](https://openvinotoolkit.github.io/openvino_notebooks/?search=Qwen3.8-27B) * Blog: [Day 0 Support for Qwen3.8–27B: Run the New Model on Intel Agentic PCs with OpenVINO™ from Day One](https://medium.com/openvino-toolkit/day-0-support-for-qwen3-8-27b-run-the-new-model-on-intel-agentic-pcs-with-openvino-from-day-one-19ca7a7790e4) * Fixed issues: * Property ENABLE_CPU_PINNING supported now on dual-socket Intel® Xeon® 6+ processors (formerly codenamed Clearwater Forest) Windows Servers. * Chat template was updated for Gemma 4 models. Now it can be parced by the Minja templating engine. * Fixed accuracy issue for the Gemma 4 26B A4B model