Intel OpenVINO 发布: 2025.4.1

来源摘要

> **_NOTE:_** Please continue using OpenVINO 2025.4 release unless you require the specific bug fixes addressed in the 2025.4.1 version. # Summary of improvements * Preview: Mixture of Experts (MoE) models optimized for CPUs and GPUs, validated for GPT-OSS 20B model. How to convert model: optimum-cli export openvino -m "openai/gpt-oss-20b" out_dir --weight-format int4 * Fixed issue ID 174531: Accuracy regression of Mistral-7b-instruct-v0.2 and Mistral-7b-instruct-v0.3 on all devices when executed with OpenVINO GenAI. As a workaround, use the IR converted with OpenVINO 2025.3. * Fixed issue ID 176777: Using the callback parameter with the Python API call generate() in Text2ImagePipeline, Image2ImagePipeline, InpaintingPipeline may cause the process to hang. As a workaround, do not use the callback parameter. C++ implementations was not affected. * Resolved an issue in the NPU plugin where the Level Zero (L0) context was implemented as a static global object and only destroyed during DLL unload, even after unload_plugin() was called. This behavior prevented the driver from spawning threads required for certain optimizations and features. You can find OpenVINO™ toolkit 2025.4.1 release here: * [Download archives*](https://storage.openvinotoolkit.org/repositories/openvino/packages/2025.4.1/) with OpenVINO™ * [OpenVINO™](https://pypi.org/project/openvino/2025.4.1/) for Python: `pip install openvino==2025.4.1`