[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"similar-uxlfoundation--scikit-learn-intelex":3,"tool-uxlfoundation--scikit-learn-intelex":61},[4,18,26,36,44,53],{"id":5,"name":6,"github_repo":7,"description_zh":8,"stars":9,"difficulty_score":10,"last_commit_at":11,"category_tags":12,"status":17},4358,"openclaw","openclaw\u002Fopenclaw","OpenClaw 是一款专为个人打造的本地化 AI 助手，旨在让你在自己的设备上拥有完全可控的智能伙伴。它打破了传统 AI 助手局限于特定网页或应用的束缚，能够直接接入你日常使用的各类通讯渠道，包括微信、WhatsApp、Telegram、Discord、iMessage 等数十种平台。无论你在哪个聊天软件中发送消息，OpenClaw 都能即时响应，甚至支持在 macOS、iOS 和 Android 设备上进行语音交互，并提供实时的画布渲染功能供你操控。\n\n这款工具主要解决了用户对数据隐私、响应速度以及“始终在线”体验的需求。通过将 AI 部署在本地，用户无需依赖云端服务即可享受快速、私密的智能辅助，真正实现了“你的数据，你做主”。其独特的技术亮点在于强大的网关架构，将控制平面与核心助手分离，确保跨平台通信的流畅性与扩展性。\n\nOpenClaw 非常适合希望构建个性化工作流的技术爱好者、开发者，以及注重隐私保护且不愿被单一生态绑定的普通用户。只要具备基础的终端操作能力（支持 macOS、Linux 及 Windows WSL2），即可通过简单的命令行引导完成部署。如果你渴望拥有一个懂你",349277,3,"2026-04-06T06:32:30",[13,14,15,16],"Agent","开发框架","图像","数据工具","ready",{"id":19,"name":20,"github_repo":21,"description_zh":22,"stars":23,"difficulty_score":10,"last_commit_at":24,"category_tags":25,"status":17},3808,"stable-diffusion-webui","AUTOMATIC1111\u002Fstable-diffusion-webui","stable-diffusion-webui 是一个基于 Gradio 构建的网页版操作界面，旨在让用户能够轻松地在本地运行和使用强大的 Stable Diffusion 图像生成模型。它解决了原始模型依赖命令行、操作门槛高且功能分散的痛点，将复杂的 AI 绘图流程整合进一个直观易用的图形化平台。\n\n无论是希望快速上手的普通创作者、需要精细控制画面细节的设计师，还是想要深入探索模型潜力的开发者与研究人员，都能从中获益。其核心亮点在于极高的功能丰富度：不仅支持文生图、图生图、局部重绘（Inpainting）和外绘（Outpainting）等基础模式，还独创了注意力机制调整、提示词矩阵、负向提示词以及“高清修复”等高级功能。此外，它内置了 GFPGAN 和 CodeFormer 等人脸修复工具，支持多种神经网络放大算法，并允许用户通过插件系统无限扩展能力。即使是显存有限的设备，stable-diffusion-webui 也提供了相应的优化选项，让高质量的 AI 艺术创作变得触手可及。",162132,"2026-04-05T11:01:52",[14,15,13],{"id":27,"name":28,"github_repo":29,"description_zh":30,"stars":31,"difficulty_score":32,"last_commit_at":33,"category_tags":34,"status":17},1381,"everything-claude-code","affaan-m\u002Feverything-claude-code","everything-claude-code 是一套专为 AI 编程助手（如 Claude Code、Codex、Cursor 等）打造的高性能优化系统。它不仅仅是一组配置文件，而是一个经过长期实战打磨的完整框架，旨在解决 AI 代理在实际开发中面临的效率低下、记忆丢失、安全隐患及缺乏持续学习能力等核心痛点。\n\n通过引入技能模块化、直觉增强、记忆持久化机制以及内置的安全扫描功能，everything-claude-code 能显著提升 AI 在复杂任务中的表现，帮助开发者构建更稳定、更智能的生产级 AI 代理。其独特的“研究优先”开发理念和针对 Token 消耗的优化策略，使得模型响应更快、成本更低，同时有效防御潜在的攻击向量。\n\n这套工具特别适合软件开发者、AI 研究人员以及希望深度定制 AI 工作流的技术团队使用。无论您是在构建大型代码库，还是需要 AI 协助进行安全审计与自动化测试，everything-claude-code 都能提供强大的底层支持。作为一个曾荣获 Anthropic 黑客大奖的开源项目，它融合了多语言支持与丰富的实战钩子（hooks），让 AI 真正成长为懂上",157379,2,"2026-04-15T23:32:42",[14,13,35],"语言模型",{"id":37,"name":38,"github_repo":39,"description_zh":40,"stars":41,"difficulty_score":32,"last_commit_at":42,"category_tags":43,"status":17},2271,"ComfyUI","Comfy-Org\u002FComfyUI","ComfyUI 是一款功能强大且高度模块化的视觉 AI 引擎，专为设计和执行复杂的 Stable Diffusion 图像生成流程而打造。它摒弃了传统的代码编写模式，采用直观的节点式流程图界面，让用户通过连接不同的功能模块即可构建个性化的生成管线。\n\n这一设计巧妙解决了高级 AI 绘图工作流配置复杂、灵活性不足的痛点。用户无需具备编程背景，也能自由组合模型、调整参数并实时预览效果，轻松实现从基础文生图到多步骤高清修复等各类复杂任务。ComfyUI 拥有极佳的兼容性，不仅支持 Windows、macOS 和 Linux 全平台，还广泛适配 NVIDIA、AMD、Intel 及苹果 Silicon 等多种硬件架构，并率先支持 SDXL、Flux、SD3 等前沿模型。\n\n无论是希望深入探索算法潜力的研究人员和开发者，还是追求极致创作自由度的设计师与资深 AI 绘画爱好者，ComfyUI 都能提供强大的支持。其独特的模块化架构允许社区不断扩展新功能，使其成为当前最灵活、生态最丰富的开源扩散模型工具之一，帮助用户将创意高效转化为现实。",108322,"2026-04-10T11:39:34",[14,15,13],{"id":45,"name":46,"github_repo":47,"description_zh":48,"stars":49,"difficulty_score":32,"last_commit_at":50,"category_tags":51,"status":17},6121,"gemini-cli","google-gemini\u002Fgemini-cli","gemini-cli 是一款由谷歌推出的开源 AI 命令行工具，它将强大的 Gemini 大模型能力直接集成到用户的终端环境中。对于习惯在命令行工作的开发者而言，它提供了一条从输入提示词到获取模型响应的最短路径，无需切换窗口即可享受智能辅助。\n\n这款工具主要解决了开发过程中频繁上下文切换的痛点，让用户能在熟悉的终端界面内直接完成代码理解、生成、调试以及自动化运维任务。无论是查询大型代码库、根据草图生成应用，还是执行复杂的 Git 操作，gemini-cli 都能通过自然语言指令高效处理。\n\n它特别适合广大软件工程师、DevOps 人员及技术研究人员使用。其核心亮点包括支持高达 100 万 token 的超长上下文窗口，具备出色的逻辑推理能力；内置 Google 搜索、文件操作及 Shell 命令执行等实用工具；更独特的是，它支持 MCP（模型上下文协议），允许用户灵活扩展自定义集成，连接如图像生成等外部能力。此外，个人谷歌账号即可享受免费的额度支持，且项目基于 Apache 2.0 协议完全开源，是提升终端工作效率的理想助手。",100752,"2026-04-10T01:20:03",[52,13,15,14],"插件",{"id":54,"name":55,"github_repo":56,"description_zh":57,"stars":58,"difficulty_score":32,"last_commit_at":59,"category_tags":60,"status":17},4721,"markitdown","microsoft\u002Fmarkitdown","MarkItDown 是一款由微软 AutoGen 团队打造的轻量级 Python 工具，专为将各类文件高效转换为 Markdown 格式而设计。它支持 PDF、Word、Excel、PPT、图片（含 OCR）、音频（含语音转录）、HTML 乃至 YouTube 链接等多种格式的解析，能够精准提取文档中的标题、列表、表格和链接等关键结构信息。\n\n在人工智能应用日益普及的今天，大语言模型（LLM）虽擅长处理文本，却难以直接读取复杂的二进制办公文档。MarkItDown 恰好解决了这一痛点，它将非结构化或半结构化的文件转化为模型“原生理解”且 Token 效率极高的 Markdown 格式，成为连接本地文件与 AI 分析 pipeline 的理想桥梁。此外，它还提供了 MCP（模型上下文协议）服务器，可无缝集成到 Claude Desktop 等 LLM 应用中。\n\n这款工具特别适合开发者、数据科学家及 AI 研究人员使用，尤其是那些需要构建文档检索增强生成（RAG）系统、进行批量文本分析或希望让 AI 助手直接“阅读”本地文件的用户。虽然生成的内容也具备一定可读性，但其核心优势在于为机器",93400,"2026-04-06T19:52:38",[52,14],{"id":62,"github_repo":63,"name":64,"description_en":65,"description_zh":66,"ai_summary_zh":66,"readme_en":67,"readme_zh":68,"quickstart_zh":69,"use_case_zh":70,"hero_image_url":71,"owner_login":72,"owner_name":73,"owner_avatar_url":74,"owner_bio":75,"owner_company":76,"owner_location":76,"owner_email":77,"owner_twitter":78,"owner_website":79,"owner_url":80,"languages":81,"stars":108,"forks":109,"last_commit_at":110,"license":111,"difficulty_score":32,"env_os":112,"env_gpu":113,"env_ram":114,"env_deps":115,"category_tags":122,"github_topics":123,"view_count":32,"oss_zip_url":76,"oss_zip_packed_at":76,"status":17,"created_at":138,"updated_at":139,"faqs":140,"releases":170},7918,"uxlfoundation\u002Fscikit-learn-intelex","scikit-learn-intelex"," Extension for Scikit-learn is a seamless way to speed up your Scikit-learn application","scikit-learn-intelex 是一款专为提升机器学习效率而设计的免费加速引擎，旨在让现有的 scikit-learn 代码在无需修改的情况下运行得更快。它主要解决了传统机器学习模型在训练和预测阶段耗时过长的问题，特别是在处理大规模数据时，能够显著缩短等待时间。\n\n这款工具非常适合广大 Python 开发者、数据科学家以及人工智能研究人员使用。无论您是在本地笔记本上进行实验，还是在服务器集群上部署应用，只需添加几行代码或通过命令行简单配置，即可无缝启用加速功能，同时完全保留原有的开源 API 使用习惯。\n\n其核心技术亮点在于深度利用了现代硬件的潜力。通过向量化指令、针对 AI 硬件优化的内存管理以及高效的多线程技术，scikit-learn-intelex 能够在 CPU 和 GPU 等多种硬件配置上实现高达 10 到 100 倍的性能提升，且保证数学计算的精度与原生版本完全一致。此外，它还支持多节点分布式环境，帮助用户轻松应对更复杂的计算场景。如果您希望在不重写代码的前提下大幅提升机器学习工作流的效率，scikit-learn-intelex 是一个值得尝试的专业选择。","\u003C!--\n  ~ Copyright 2018 Intel Corporation\n  ~\n  ~ Licensed under the Apache License, Version 2.0 (the \"License\");\n  ~ you may not use this file except in compliance with the License.\n  ~ You may obtain a copy of the License at\n  ~\n  ~     http:\u002F\u002Fwww.apache.org\u002Flicenses\u002FLICENSE-2.0\n  ~\n  ~ Unless required by applicable law or agreed to in writing, software\n  ~ distributed under the License is distributed on an \"AS IS\" BASIS,\n  ~ WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.\n  ~ See the License for the specific language governing permissions and\n  ~ limitations under the License.\n-->\n\n\u003Cdiv align=\"center\">\n\n\n# Extension for Scikit-learn*\n\n\u003Ch3> Speed up your scikit-learn applications for CPUs and GPUs across single- and multi-node configurations\n\n[Releases](https:\u002F\u002Fgithub.com\u002Fuxlfoundation\u002Fscikit-learn-intelex\u002Freleases)   |   [Documentation](https:\u002F\u002Fuxlfoundation.github.io\u002Fscikit-learn-intelex\u002F)   |   [Examples](https:\u002F\u002Fuxlfoundation.github.io\u002Fscikit-learn-intelex\u002Flatest\u002Fsamples.html)   |   [Support](https:\u002F\u002Fgithub.com\u002Fuxlfoundation\u002Fscikit-learn-intelex\u002Fblob\u002Fmain\u002Fdoc\u002Fsources\u002Fsupport.rst)   |  [License](https:\u002F\u002Fgithub.com\u002Fuxlfoundation\u002Fscikit-learn-intelex\u002Fblob\u002Fmaster\u002FLICENSE)   \n\n\n[![Build Status](https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Fuxlfoundation_scikit-learn-intelex_readme_5881a66031b5.png)](https:\u002F\u002Fdev.azure.com\u002Fdaal\u002Fdaal4py\u002F_build\u002Flatest?definitionId=9&branchName=main)\n[![Coverity Scan Build Status](https:\u002F\u002Fscan.coverity.com\u002Fprojects\u002F21716\u002Fbadge.svg)](https:\u002F\u002Fscan.coverity.com\u002Fprojects\u002Fdaal4py)\n[![OpenSSF Scorecard](https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Fuxlfoundation_scikit-learn-intelex_readme_fd439a7b9f24.png)](https:\u002F\u002Fsecurityscorecards.dev\u002Fviewer\u002F?uri=github.com\u002Fuxlfoundation\u002Fscikit-learn-intelex)\n[![Join the community on GitHub Discussions](https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Fuxlfoundation_scikit-learn-intelex_readme_5a511d467bf6.png)](https:\u002F\u002Fgithub.com\u002Fuxlfoundation\u002Fscikit-learn-intelex\u002Fdiscussions)\n[![PyPI Version](https:\u002F\u002Fimg.shields.io\u002Fpypi\u002Fv\u002Fscikit-learn-intelex)](https:\u002F\u002Fpypi.org\u002Fproject\u002Fscikit-learn-intelex\u002F)\n[![Conda Version](https:\u002F\u002Fimg.shields.io\u002Fconda\u002Fvn\u002Fconda-forge\u002Fscikit-learn-intelex)](https:\u002F\u002Fanaconda.org\u002Fconda-forge\u002Fscikit-learn-intelex)\n[![python version](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002Fpython-3.10%20%7C%203.11%20%7C%203.12%20%7C%203.13%20%7C%203.14-blue)](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002Fpython-3.10%20%7C%203.11%20%7C%203.12%20%7C%203.13%20%7C%203.14-blue)\n[![scikit-learn supported versions](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002Fsklearn-1.0%20%7C%201.5%20%7C%201.6%20%7C%201.7%20%7C%201.8-blue)](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002Fsklearn-1.0%20%7C%201.5%20%7C%201.6%20%7C%201.7%20%7C%201.8-blue)\n\n---\n\u003C\u002Fh3>\n\n\u003Cdiv align=\"left\">\n\n## Overview\n\nExtension for Scikit-learn is a **free software AI accelerator** designed to deliver over **10-100X** acceleration to your existing scikit-learn code.\nThe software acceleration is achieved with vector instructions, AI hardware-specific memory optimizations, threading, and optimizations.\n\n\nWith Extension for Scikit-learn, you can:\n\n* Speed up training and inference by up to 100x with equivalent mathematical accuracy\n* Benefit from performance improvements across different hardware configurations, including [GPUs](https:\u002F\u002Fuxlfoundation.github.io\u002Fscikit-learn-intelex\u002Flatest\u002Foneapi-gpu.html) and [multi-GPU](https:\u002F\u002Fuxlfoundation.github.io\u002Fscikit-learn-intelex\u002Flatest\u002Fdistributed-mode.html) configurations\n* Integrate the extension into your existing Scikit-learn applications without code modifications\n* Continue to use the open-source scikit-learn API\n* Enable and disable the extension with a couple of lines of code or at the command line\n\n## Acceleration\n\n![](https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Fuxlfoundation_scikit-learn-intelex_readme_709b0215393d.png)\n\n[Benchmarks code](https:\u002F\u002Fgithub.com\u002FIntelPython\u002Fscikit-learn_bench)\n\n## Optimizations\n\nEasiest way to benefit from accelerations from the extension is by patching scikit-learn with it:\n\n- **Enable CPU optimizations**\n\n    ```python\n    import numpy as np\n    from sklearnex import patch_sklearn\n    patch_sklearn()\n\n    from sklearn.cluster import DBSCAN\n\n    X = np.array([[1., 2.], [2., 2.], [2., 3.],\n                  [8., 7.], [8., 8.], [25., 80.]], dtype=np.float32)\n    clustering = DBSCAN(eps=3, min_samples=2).fit(X)\n    ```\n\n- **Enable GPU optimizations**\n\n    _Note: executing on GPU has [additional system software requirements](https:\u002F\u002Fwww.intel.com\u002Fcontent\u002Fwww\u002Fus\u002Fen\u002Fdeveloper\u002Farticles\u002Fsystem-requirements\u002Fintel-oneapi-dpcpp-system-requirements.html) - see [details](https:\u002F\u002Fuxlfoundation.github.io\u002Fscikit-learn-intelex\u002Flatest\u002Foneapi-gpu.html)._\n\n    ```python\n    import numpy as np\n    from sklearnex import patch_sklearn, config_context\n    patch_sklearn()\n\n    from sklearn.cluster import DBSCAN\n\n    X = np.array([[1., 2.], [2., 2.], [2., 3.],\n                  [8., 7.], [8., 8.], [25., 80.]], dtype=np.float32)\n    with config_context(target_offload=\"gpu:0\"):\n        clustering = DBSCAN(eps=3, min_samples=2).fit(X)\n    ```\n\n:eyes: Read about [other ways to patch scikit-learn](https:\u002F\u002Fuxlfoundation.github.io\u002Fscikit-learn-intelex\u002Flatest\u002Fquick-start.html#patching).\n\n:eyes: Check out available [notebooks](https:\u002F\u002Fgithub.com\u002Fuxlfoundation\u002Fscikit-learn-intelex\u002Ftree\u002Fmaster\u002Fexamples\u002Fnotebooks) for more examples.\n\n### Usage without patching\n\nAlternatively, all functionalities are also available under a separate module which can be imported directly, without involving any patching.\n\n* To run on CPU:\n\n  ```python\n  import numpy as np\n  from sklearnex.cluster import DBSCAN\n\n  X = np.array([[1., 2.], [2., 2.], [2., 3.],\n                [8., 7.], [8., 8.], [25., 80.]], dtype=np.float32)\n  clustering = DBSCAN(eps=3, min_samples=2).fit(X)\n  ```\n\n* To run on GPU:\n\n  ```python\n  import numpy as np\n  from sklearnex import config_context\n  from sklearnex.cluster import DBSCAN\n\n  X = np.array([[1., 2.], [2., 2.], [2., 3.],\n                [8., 7.], [8., 8.], [25., 80.]], dtype=np.float32)\n  with config_context(target_offload=\"gpu:0\"):\n      clustering = DBSCAN(eps=3, min_samples=2).fit(X)\n  ```\n\n## Installation\n\nTo install Extension for Scikit-learn, run:\n\n```shell\npip install scikit-learn-intelex\n```\n\nPackage is also offered through other channels such as conda-forge. See all installation instructions in the [Installation Guide](https:\u002F\u002Fuxlfoundation.github.io\u002Fscikit-learn-intelex\u002Flatest\u002Fquick-start.html#installation).\n\n## Documentation\n\n* [Quick Start](https:\u002F\u002Fuxlfoundation.github.io\u002Fscikit-learn-intelex\u002Flatest\u002Fquick-start.html)\n* [Documentation and Tutorials](https:\u002F\u002Fuxlfoundation.github.io\u002Fscikit-learn-intelex\u002Flatest\u002Findex.html)\n* [Release Notes](https:\u002F\u002Fgithub.com\u002Fuxlfoundation\u002Fscikit-learn-intelex\u002Freleases)\n* [Medium Blogs](https:\u002F\u002Fuxlfoundation.github.io\u002Fscikit-learn-intelex\u002Flatest\u002Fblogs.html)\n* [Code of Conduct](https:\u002F\u002Fgithub.com\u002Fuxlfoundation\u002Fscikit-learn-intelex\u002Fblob\u002Fmain\u002Fdoc\u002Fsources\u002Fcode-of-conduct.rst)\n\n### Extension and oneDAL\n\nAcceleration in patched scikit-learn classes is achieved by replacing calls to scikit-learn with calls to oneDAL (oneAPI Data Analytics Library) behind the scenes:\n- [oneAPI Data Analytics Library](https:\u002F\u002Fgithub.com\u002Fuxlfoundation\u002FoneDAL)\n\n## Samples & Examples\n\n* [Examples](https:\u002F\u002Fgithub.com\u002Fuxlfoundation\u002Fscikit-learn-intelex\u002Ftree\u002Fmaster\u002Fexamples\u002Fnotebooks)\n* [Samples](https:\u002F\u002Fuxlfoundation.github.io\u002Fscikit-learn-intelex\u002Flatest\u002Fsamples.html)\n* [Kaggle Kernels](https:\u002F\u002Fuxlfoundation.github.io\u002Fscikit-learn-intelex\u002Flatest\u002Fkaggle.html)\n\n\n## How to Contribute\n\nWe welcome community contributions, check our [Contributing Guidelines](https:\u002F\u002Fgithub.com\u002Fuxlfoundation\u002Fscikit-learn-intelex\u002Fblob\u002Fmain\u002Fdoc\u002Fsources\u002Fcontribute.rst) to learn more.\n\n------------------------------------------------------------------------\n\\* The Intel logo, and other Intel marks are trademarks of Intel Corporation or its subsidiaries. Other names and brands may be claimed as the property of others.\n\n","\u003C!--\n  ~ Copyright 2018 Intel Corporation\n  ~\n  ~ Licensed under the Apache License, Version 2.0 (the \"License\");\n  ~ you may not use this file except in compliance with the License.\n  ~ You may obtain a copy of the License at\n  ~\n  ~     http:\u002F\u002Fwww.apache.org\u002Flicenses\u002FLICENSE-2.0\n  ~\n  ~ Unless required by applicable law or agreed to in writing, software\n  ~ distributed under the License is distributed on an \"AS IS\" BASIS,\n  ~ WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.\n  ~ See the License for the specific language governing permissions and\n  ~ limitations under the License.\n-->\n\n\u003Cdiv align=\"center\">\n\n\n# Scikit-learn 扩展*\n\n\u003Ch3> 在单节点和多节点配置下，为 CPU 和 GPU 加速您的 scikit-learn 应用程序\n\n[发布版本](https:\u002F\u002Fgithub.com\u002Fuxlfoundation\u002Fscikit-learn-intelex\u002Freleases)   |   [文档](https:\u002F\u002Fuxlfoundation.github.io\u002Fscikit-learn-intelex\u002F)   |   [示例](https:\u002F\u002Fuxlfoundation.github.io\u002Fscikit-learn-intelex\u002Flatest\u002Fsamples.html)   |   [支持](https:\u002F\u002Fgithub.com\u002Fuxlfoundation\u002Fscikit-learn-intelex\u002Fblob\u002Fmain\u002Fdoc\u002Fsources\u002Fsupport.rst)   |  [许可证](https:\u002F\u002Fgithub.com\u002Fuxlfoundation\u002Fscikit-learn-intelex\u002Fblob\u002Fmaster\u002FLICENSE)   \n\n\n[![构建状态](https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Fuxlfoundation_scikit-learn-intelex_readme_5881a66031b5.png)](https:\u002F\u002Fdev.azure.com\u002Fdaal\u002Fdaal4py\u002F_build\u002Flatest?definitionId=9&branchName=main)\n[![Coverity Scan 构建状态](https:\u002F\u002Fscan.coverity.com\u002Fprojects\u002F21716\u002Fbadge.svg)](https:\u002F\u002Fscan.coverity.com\u002Fprojects\u002Fdaal4py)\n[![OpenSSF 得分卡](https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Fuxlfoundation_scikit-learn-intelex_readme_fd439a7b9f24.png)](https:\u002F\u002Fsecurityscorecards.dev\u002Fviewer\u002F?uri=github.com\u002Fuxlfoundation\u002Fscikit-learn-intelex)\n[![加入 GitHub Discussions 社区](https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Fuxlfoundation_scikit-learn-intelex_readme_5a511d467bf6.png)](https:\u002F\u002Fgithub.com\u002Fuxlfoundation\u002Fscikit-learn-intelex\u002Fdiscussions)\n[![PyPI 版本](https:\u002F\u002Fimg.shields.io\u002Fpypi\u002Fv\u002Fscikit-learn-intelex)](https:\u002F\u002Fpypi.org\u002Fproject\u002Fscikit-learn-intelex\u002F)\n[![Conda 版本](https:\u002F\u002Fimg.shields.io\u002Fconda\u002Fvn\u002Fconda-forge\u002Fscikit-learn-intelex)](https:\u002F\u002Fanaconda.org\u002Fconda-forge\u002Fscikit-learn-intelex)\n[![Python 版本](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002Fpython-3.10%20%7C%203.11%20%7C%203.12%20%7C%203.13%20%7C%203.14-blue)](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002Fpython-3.10%20%7C%203.11%20%7C%203.12%20%7C%203.13%20%7C%203.14-blue)\n[![scikit-learn 支持的版本](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002Fsklearn-1.0%20%7C%201.5%20%7C%201.6%20%7C%201.7%20%7C%201.8-blue)](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002Fsklearn-1.0%20%7C%201.5%20%7C%201.6%20%7C%201.7%20%7C%201.8-blue)\n\n---\n\u003C\u002Fh3>\n\n\u003Cdiv align=\"left\">\n\n## 概述\n\nScikit-learn 扩展是一款 **免费的 AI 加速器软件**，旨在为您的现有 scikit-learn 代码提供超过 **10-100 倍** 的加速。这种软件加速是通过向量化指令、针对 AI 硬件的内存优化、多线程以及各种优化技术实现的。\n\n借助 Scikit-learn 扩展，您可以：\n\n* 在保持同等数学精度的前提下，将训练和推理速度提升至原来的 100 倍\n* 在不同的硬件配置上获得性能提升，包括 [GPU](https:\u002F\u002Fuxlfoundation.github.io\u002Fscikit-learn-intelex\u002Flatest\u002Foneapi-gpu.html) 和 [多 GPU](https:\u002F\u002Fuxlfoundation.github.io\u002Fscikit-learn-intelex\u002Flatest\u002Fdistributed-mode.html) 配置\n* 将该扩展无缝集成到您现有的 Scikit-learn 应用程序中，无需修改代码\n* 继续使用开源的 scikit-learn API\n* 仅需几行代码或在命令行中即可启用或禁用该扩展\n\n## 加速效果\n\n![](https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Fuxlfoundation_scikit-learn-intelex_readme_709b0215393d.png)\n\n[基准测试代码](https:\u002F\u002Fgithub.com\u002FIntelPython\u002Fscikit-learn_bench)\n\n## 优化方法\n\n从该扩展中受益最简单的方式就是将其“补丁”应用到 scikit-learn 中：\n\n- **启用 CPU 优化**\n\n    ```python\n    import numpy as np\n    from sklearnex import patch_sklearn\n    patch_sklearn()\n\n    from sklearn.cluster import DBSCAN\n\n    X = np.array([[1., 2.], [2., 2.], [2., 3.],\n                  [8., 7.], [8., 8.], [25., 80.]], dtype=np.float32)\n    clustering = DBSCAN(eps=3, min_samples=2).fit(X)\n    ```\n\n- **启用 GPU 优化**\n\n    _注意：在 GPU 上运行需要满足 [额外的系统软件要求](https:\u002F\u002Fwww.intel.com\u002Fcontent\u002Fwww\u002Fus\u002Fen\u002Fdeveloper\u002Farticles\u002Fsystem-requirements\u002Fintel-oneapi-dpcpp-system-requirements.html) - 详情请参阅 [此处](https:\u002F\u002Fuxlfoundation.github.io\u002Fscikit-learn-intelex\u002Flatest\u002Foneapi-gpu.html)。_\n\n    ```python\n    import numpy as np\n    from sklearnex import patch_sklearn, config_context\n    patch_sklearn()\n\n    from sklearn.cluster import DBSCAN\n\n    X = np.array([[1., 2.], [2., 2.], [2., 3.],\n                  [8., 7.], [8., 8.], [25., 80.]], dtype=np.float32)\n    with config_context(target_offload=\"gpu:0\"):\n        clustering = DBSCAN(eps=3, min_samples=2).fit(X)\n    ```\n\n:eyes: 了解 [其他补丁 scikit-learn 的方法](https:\u002F\u002Fuxlfoundation.github.io\u002Fscikit-learn-intelex\u002Flatest\u002Fquick-start.html#patching)。\n\n:eyes: 查看可用的 [笔记本](https:\u002F\u002Fgithub.com\u002Fuxlfoundation\u002Fscikit-learn-intelex\u002Ftree\u002Fmaster\u002Fexamples\u002Fnotebooks)，获取更多示例。\n\n### 不使用补丁的用法\n\n此外，所有功能也可以通过单独的模块直接导入使用，而无需进行任何补丁操作。\n\n* 在 CPU 上运行：\n\n  ```python\n  import numpy as np\n  from sklearnex.cluster import DBSCAN\n\n  X = np.array([[1., 2.], [2., 2.], [2., 3.],\n                [8., 7.], [8., 8.], [25., 80.]], dtype=np.float32)\n  clustering = DBSCAN(eps=3, min_samples=2).fit(X)\n  ```\n\n* 在 GPU 上运行：\n\n  ```python\n  import numpy as np\n  from sklearnex import config_context\n  from sklearnex.cluster import DBSCAN\n\n  X = np.array([[1., 2.], [2., 2.], [2., 3.],\n                [8., 7.], [8., 8.], [25., 80.]], dtype=np.float32)\n  with config_context(target_offload=\"gpu:0\"):\n      clustering = DBSCAN(eps=3, min_samples=2).fit(X)\n  ```\n\n## 安装\n\n要安装 Scikit-learn 扩展，请运行以下命令：\n\n```shell\npip install scikit-learn-intelex\n```\n\n该软件包也可通过 conda-forge 等其他渠道获取。完整的安装说明请参阅 [安装指南](https:\u002F\u002Fuxlfoundation.github.io\u002Fscikit-learn-intelex\u002Flatest\u002Fquick-start.html#installation)。\n\n## 文档\n\n* [快速入门](https:\u002F\u002Fuxlfoundation.github.io\u002Fscikit-learn-intelex\u002Flatest\u002Fquick-start.html)\n* [文档与教程](https:\u002F\u002Fuxlfoundation.github.io\u002Fscikit-learn-intelex\u002Flatest\u002Findex.html)\n* [发布说明](https:\u002F\u002Fgithub.com\u002Fuxlfoundation\u002Fscikit-learn-intelex\u002Freleases)\n* [Medium 博客](https:\u002F\u002Fuxlfoundation.github.io\u002Fscikit-learn-intelex\u002Flatest\u002Fblogs.html)\n* [行为准则](https:\u002F\u002Fgithub.com\u002Fuxlfoundation\u002Fscikit-learn-intelex\u002Fblob\u002Fmain\u002Fdoc\u002Fsources\u002Fcode-of-conduct.rst)\n\n### 扩展与 oneDAL\n\n通过在底层将 scikit-learn 的调用替换为 oneDAL（oneAPI 数据分析库）的调用，从而实现对打补丁后的 scikit-learn 类的加速：\n- [oneAPI 数据分析库](https:\u002F\u002Fgithub.com\u002Fuxlfoundation\u002FoneDAL)\n\n## 示例与样例\n\n* [示例](https:\u002F\u002Fgithub.com\u002Fuxlfoundation\u002Fscikit-learn-intelex\u002Ftree\u002Fmaster\u002Fexamples\u002Fnotebooks)\n* [样例](https:\u002F\u002Fuxlfoundation.github.io\u002Fscikit-learn-intelex\u002Flatest\u002Fsamples.html)\n* [Kaggle Notebook](https:\u002F\u002Fuxlfoundation.github.io\u002Fscikit-learn-intelex\u002Flatest\u002Fkaggle.html)\n\n\n## 如何贡献\n\n我们欢迎社区贡献，请查看我们的[贡献指南](https:\u002F\u002Fgithub.com\u002Fuxlfoundation\u002Fscikit-learn-intelex\u002Fblob\u002Fmain\u002Fdoc\u002Fsources\u002Fcontribute.rst)以了解更多信息。\n\n------------------------------------------------------------------------\n\\* 英特尔标志及其他英特尔标识均为英特尔公司或其子公司的商标。其他名称和品牌可能属于各自所有者。","# scikit-learn-intelex 快速上手指南\n\n`scikit-learn-intelex` 是一个免费的 AI 加速扩展工具，旨在无需修改代码即可将现有的 scikit-learn 应用速度提升 **10-100 倍**。它通过利用 CPU 向量指令、内存优化及多线程技术（以及可选的 GPU 加速）来实现性能飞跃，同时完全保持与开源 scikit-learn API 的兼容性。\n\n## 环境准备\n\n在开始之前，请确保您的开发环境满足以下要求：\n\n*   **操作系统**：Linux, Windows, 或 macOS。\n*   **Python 版本**：支持 Python 3.10, 3.11, 3.12, 3.13, 3.14。\n*   **scikit-learn 版本**：支持 1.0, 1.5, 1.6, 1.7, 1.8 等版本。\n*   **前置依赖**：需已安装 `numpy` 和 `scikit-learn`。\n*   **GPU 加速额外要求**（可选）：\n    *   若需启用 GPU 加速，需安装 Intel oneAPI DPC++ 编译器及相关驱动。\n    *   详见 [Intel oneAPI 系统要求](https:\u002F\u002Fwww.intel.com\u002Fcontent\u002Fwww\u002Fus\u002Fen\u002Fdeveloper\u002Farticles\u002Fsystem-requirements\u002Fintel-oneapi-dpcpp-system-requirements.html)。\n\n## 安装步骤\n\n推荐使用 `pip` 进行安装。国内开发者可使用清华或阿里镜像源以加快下载速度。\n\n### 方式一：使用 pip 安装（推荐）\n\n```shell\n# 使用默认源\npip install scikit-learn-intelex\n\n# 或使用国内镜像源（推荐）\npip install scikit-learn-intelex -i https:\u002F\u002Fpypi.tuna.tsinghua.edu.cn\u002Fsimple\n```\n\n### 方式二：使用 Conda 安装\n\n如果您使用 Anaconda 或 Miniconda：\n\n```shell\nconda install -c conda-forge scikit-learn-intelex\n```\n\n## 基本使用\n\n该工具提供两种主要使用模式：**全局补丁模式**（推荐，无需改代码逻辑）和**直接导入模式**。\n\n### 模式一：全局补丁模式（最简单）\n\n只需两行代码即可加速整个脚本中所有的 scikit-learn 调用。\n\n#### 1. CPU 加速示例\n\n```python\nimport numpy as np\nfrom sklearnex import patch_sklearn\n\n# 启用加速补丁\npatch_sklearn()\n\n# 后续导入的 sklearn 模块将自动使用加速版本\nfrom sklearn.cluster import DBSCAN\n\nX = np.array([[1., 2.], [2., 2.], [2., 3.],\n              [8., 7.], [8., 8.], [25., 80.]], dtype=np.float32)\n\n# 无需修改任何参数，自动加速\nclustering = DBSCAN(eps=3, min_samples=2).fit(X)\nprint(clustering.labels_)\n```\n\n#### 2. GPU 加速示例\n\n若需指定在 GPU 上运行，可结合 `config_context` 使用：\n\n```python\nimport numpy as np\nfrom sklearnex import patch_sklearn, config_context\n\n# 启用加速补丁\npatch_sklearn()\n\nfrom sklearn.cluster import DBSCAN\n\nX = np.array([[1., 2.], [2., 2.], [2., 3.],\n              [8., 7.], [8., 8.], [25., 80.]], dtype=np.float32)\n\n# 指定目标设备为 GPU\nwith config_context(target_offload=\"gpu:0\"):\n    clustering = DBSCAN(eps=3, min_samples=2).fit(X)\n    print(clustering.labels_)\n```\n\n### 模式二：直接导入模式（不补丁）\n\n如果您不希望影响全局环境，可以直接从 `sklearnex` 子模块导入特定的加速算法类。\n\n#### 1. CPU 加速\n\n```python\nimport numpy as np\n# 直接从 sklearnex 导入加速版的 DBSCAN\nfrom sklearnex.cluster import DBSCAN\n\nX = np.array([[1., 2.], [2., 2.], [2., 3.],\n              [8., 7.], [8., 8.], [25., 80.]], dtype=np.float32)\n\nclustering = DBSCAN(eps=3, min_samples=2).fit(X)\n```\n\n#### 2. GPU 加速\n\n```python\nimport numpy as np\nfrom sklearnex import config_context\nfrom sklearnex.cluster import DBSCAN\n\nX = np.array([[1., 2.], [2., 2.], [2., 3.],\n              [8., 7.], [8., 8.], [25., 80.]], dtype=np.float32)\n\nwith config_context(target_offload=\"gpu:0\"):\n    clustering = DBSCAN(eps=3, min_samples=2).fit(X)\n```\n\n> **提示**：更多支持的算法列表及高级用法（如多节点分布式训练），请参阅官方 [文档](https:\u002F\u002Fuxlfoundation.github.io\u002Fscikit-learn-intelex\u002Flatest\u002F) 和 [示例 notebooks](https:\u002F\u002Fgithub.com\u002Fuxlfoundation\u002Fscikit-learn-intelex\u002Ftree\u002Fmaster\u002Fexamples\u002Fnotebooks)。","某电商数据团队需要在每日凌晨对千万级用户行为数据进行聚类分析，以更新推荐系统的用户分群模型。\n\n### 没有 scikit-learn-intelex 时\n- **训练耗时过长**：使用原生 Scikit-learn 的 K-Means 算法处理千万级数据时，单次训练往往需要数小时，经常导致任务无法在业务低峰期窗口内完成。\n- **硬件资源闲置**：尽管服务器配备了高性能多核 CPU，但原生算法无法充分调用向量指令集和多线程并行能力，CPU 利用率长期偏低。\n- **迭代效率低下**：数据科学家调整参数后需等待漫长的重训过程，严重拖慢了模型调优和实验验证的节奏。\n- **扩容成本高昂**：为了缩短计算时间，团队被迫考虑增加更多计算节点或升级硬件，导致基础设施预算大幅上升。\n\n### 使用 scikit-learn-intelex 后\n- **速度显著提升**：仅需导入库并启用加速，K-Means 训练时间从数小时缩短至几分钟，轻松实现 10-100 倍的性能飞跃，确保任务准时交付。\n- **硬件潜能释放**：scikit-learn-intelex 自动利用 CPU 的向量指令和内存优化技术，将处理器算力吃满，无需修改任何底层算法代码。\n- **研发流程提速**：模型迭代周期从“天”级变为“分钟”级，算法工程师可以快速验证多种假设，大幅提升了模型最终效果。\n- **成本有效节约**：在现有硬件配置下即可满足性能需求，避免了不必要的集群扩容开支，实现了降本增效。\n\nscikit-learn-intelex 通过无缝加速现有代码，让传统机器学习任务在无需重构的前提下获得深度学习般的推理与训练效率。","https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Fuxlfoundation_scikit-learn-intelex_709b0215.png","uxlfoundation","Unified Acceleration (UXL) Foundation","https:\u002F\u002Foss.gittoolsai.com\u002Favatars\u002Fuxlfoundation_bc0c99d1.png","Building a multi-architecture and multi-vendor software ecosystem for all accelerators",null,"operations@uxlfoundation.org","UXLfoundation","https:\u002F\u002Fuxlfoundation.org","https:\u002F\u002Fgithub.com\u002Fuxlfoundation",[82,86,90,94,98,101,105],{"name":83,"color":84,"percentage":85},"Python","#3572A5",80.5,{"name":87,"color":88,"percentage":89},"C++","#f34b7d",17.8,{"name":91,"color":92,"percentage":93},"Cython","#fedf5b",0.6,{"name":95,"color":96,"percentage":97},"Shell","#89e051",0.4,{"name":99,"color":100,"percentage":97},"CMake","#DA3434",{"name":102,"color":103,"percentage":104},"C","#555555",0.2,{"name":106,"color":107,"percentage":104},"Batchfile","#C1F12E",1337,185,"2026-04-15T13:14:03","Apache-2.0","Linux, Windows, macOS","非必需（支持 CPU 和 GPU）。GPU 加速需 Intel GPU（基于 oneAPI\u002FDPC++），具体型号及显存未说明；不支持 NVIDIA CUDA。需安装 Intel oneAPI DPC++ 系统软件。","未说明",{"notes":116,"python":117,"dependencies":118},"该工具是 scikit-learn 的免费加速扩展，无需修改代码即可通过 patch 方式启用。CPU 模式下利用向量指令和多线程优化；GPU 模式需额外安装 Intel oneAPI DPC++ 环境。支持单节点及多节点分布式配置。可通过 'patch_sklearn()' 全局启用或直接导入 'sklearnex' 模块使用。","3.10 | 3.11 | 3.12 | 3.13 | 3.14",[119,120,121],"scikit-learn (1.0, 1.5, 1.6, 1.7, 1.8)","numpy","oneDAL (oneAPI Data Analytics Library)",[14,52,16],[124,125,126,127,128,129,130,131,132,133,134,135,136,137],"oneapi","scikit-learn","machine-learning-algorithms","data-analysis","machine-learning","python","swrepo","ai-machine-learning","big-data","analytics","ai-training","ai-inference","gpu","hacktoberfest","2026-03-27T02:49:30.150509","2026-04-16T08:12:12.654731",[141,146,151,156,161,165],{"id":142,"question_zh":143,"answer_zh":144,"source_url":145},35447,"是否可以使用 OpenBLAS\u002FLAPACK 和 OpenMP 代替 oneMKL 和 oneTBB 来构建 scikit-learn-intelex？","是的，可以使用 OpenBLAS 后端进行构建。有用户确认成功使用 OpenBLAS 后端完成了构建，但需注意常规的 fpkmkl 后端可能会出现问题。目前项目中可能没有直接的配置文件用于切换不同的数学库和线程库，通常需要修改构建脚本或 Makefile 来实现。","https:\u002F\u002Fgithub.com\u002Fuxlfoundation\u002Fscikit-learn-intelex\u002Fissues\u002F1294",{"id":147,"question_zh":148,"answer_zh":149,"source_url":150},35448,"使用 Intelex 加速 SVC 训练时遇到内存溢出（OOM）错误怎么办？","这是一个已知的内存泄漏问题，不仅影响 SVC，也影响 SVR。该问题已在相关 PR (#2540) 中得到修复，预计将在 2025.7 版本发布后可用。在此之前，建议暂时使用原生 scikit-learn 或关注后续版本更新。","https:\u002F\u002Fgithub.com\u002Fuxlfoundation\u002Fscikit-learn-intelex\u002Fissues\u002F1010",{"id":152,"question_zh":153,"answer_zh":154,"source_url":155},35449,"在 Windows 10 上运行 daal4py 或 LightGBM 集成时报错\"Intel oneDAL FATAL ERROR: Cannot load ... dll\"如何解决？","该问题通常与虚拟环境（virtualenv）中 DLL 路径加载失败有关。官方已合并了针对 virtualenv 问题的修复补丁（PR #488）。请确保升级到包含此修复的最新版本。如果问题依旧，检查 `__init__.py` 中的 `path_to_libs` 配置是否正确指向了包含 DLL 文件的目录（例如 `..\\\\Library\\\\bin`）。","https:\u002F\u002Fgithub.com\u002Fuxlfoundation\u002Fscikit-learn-intelex\u002Fissues\u002F514",{"id":157,"question_zh":158,"answer_zh":159,"source_url":160},35450,"在 Ubuntu 18.04 的 Anaconda\u002FJupyter 环境中导入 daal4py 报错\"ModuleNotFoundError: No module named 'daal4py'\"怎么办？","这通常是由于当前激活的 Conda 环境中未安装 daal4py 导致的。解决方案是创建一个新的 Conda 环境并安装所需包。可以使用命令 `conda create --name \u003Cenv_name> --file \u003Cpackage_list.txt>` 创建环境，然后通过 `conda activate \u003Cenv_name>` 激活它。如果问题持续，尝试重新安装 Ubuntu 或重建 Conda 环境往往能解决依赖冲突问题。","https:\u002F\u002Fgithub.com\u002Fuxlfoundation\u002Fscikit-learn-intelex\u002Fissues\u002F188",{"id":162,"question_zh":163,"answer_zh":164,"source_url":145},35451,"如何解释 oneDAL Makefile 中关于 CPU 架构替换的代码逻辑（如 sse2 替换为 nrh）？","Makefile 中的 `$(subst ...)` 函数用于文本替换。代码逻辑是将通用的向量扩展指令集名称（如 `sse2`, `avx2`, `avx512`）临时重命名为专有的 CPU 代际代号（如 `nrh`, `neh`, `hsw`, `skx`）。这样做的目的是为了能够针对特定的 CPU 代数进行优化编译，确保生成的库文件能利用特定硬件的最先进指令集。",{"id":166,"question_zh":167,"answer_zh":168,"source_url":169},35452,"在使用 config_context 设置 target_offload=\"gpu:0\" 时，DBSCAN 似乎仍在 CPU 上运行而未使用 GPU，如何排查？","首先确认 GPU 设备是否被正确识别。可以使用 `dpctl.SyclQueue(\"gpu\")` 创建设备队列，并调用 `q.sycl_device.is_gpu` 验证是否为真，使用 `q.print_device_info()` 打印设备详细信息（如 Intel Arc 显卡）。如果设备识别正常但仍无 GPU 负载，可能是该算法版本对 GPU 的支持尚不完善或数据量过小导致调度开销掩盖了加速效果。确保已正确调用 `patch_sklearn()` 且上下文管理器包裹了拟合过程。","https:\u002F\u002Fgithub.com\u002Fuxlfoundation\u002Fscikit-learn-intelex\u002Fissues\u002F1368",[171,176,181,186,191,196,201,206,211,216,221,226,231,236,241,246,251,256,261,266],{"id":172,"version":173,"summary_zh":174,"released_at":175},280526,"2025.11.0","Scikit-learn* 扩展很荣幸地推出 2025.11.0 版本！\n\n## :triangular_flag_on_post: 移除与 ABI 兼容性\n\n* 以下功能已弃用，将在未来的版本中移除：\n  * 内部 dpctl 张量处理功能\n\n## :rotating_light: 新特性\n\n* 引入了 Scikit-learn* 扩展的新功能：\n  * 在集成算法中启用了数组 API 支持\n  * 在 `SVM` 算法中启用了数组 API 支持\n\n## :beetle: 错误修复\n\n* 修复了 `LogisticRegressionCV` 的打补丁问题\n* 将 sklearnex 和 daal4py 的打补丁映射分离；修复了为被打补丁的对象使用唯一 ID 的问题\n* 修复了稀疏数据框的处理问题\n* 修复了对 scikit-learn 1.8 的支持问题\n* 修复了 numpy 2.4 标量转换的问题\n\n## 致谢\n\n感谢所有帮助我们实现 2025.11.0 版本发布的人！\n\n@Alexandr-Solovev、@Vika-F、@david-cortes-intel、@icfaust、@napetrov、@maria-Petrova、@homksei、@ahuber21、@ethanglaser、@razdoburdin、@avolkov-intel、@yuejiaointel、@DDJHB、@kjackiew、@richardnorth3\n\n**完整变更日志**：https:\u002F\u002Fgithub.com\u002Fuxlfoundation\u002Fscikit-learn-intelex\u002Fcompare\u002F2025.10.1...2025.11.0","2026-03-09T11:14:03",{"id":177,"version":178,"summary_zh":179,"released_at":180},280527,"2025.10.1","Scikit-learn* 扩展很荣幸地推出 2025.10.1 版本！\n\n## :hammer: 库工程\n\n* 为 Scikit-learn* 扩展包添加了对 Python 3.14 的支持\n\n## :beetle: 错误修复\n\n* 修复了 sklearn1.8 中 `LogisticRegression` 的匹配函数签名和默认参数\n* 修复了 NumPy 2.4 的标量转换问题\n\n## 致谢\n感谢所有帮助我们实现 2025.10.1 版本发布的朋友们！\n\n@Alexandr-Solovev、@Vika-F、@david-cortes-intel、@icfaust、@napetrov、@maria-Petrova、@homksei、@ahuber21、@ethanglaser、@razdoburdin、@avolkov-intel、@yuejiaointel、@DDJHB、@kjackiew、@richardnorth3\n\n**完整变更日志**：https:\u002F\u002Fgithub.com\u002Fuxlfoundation\u002Fscikit-learn-intelex\u002Fcompare\u002F2025.10.0...2025.10.1","2026-01-23T15:21:56",{"id":182,"version":183,"summary_zh":184,"released_at":185},280528,"2025.10.0","Scikit-learn* 扩展很荣幸地推出 2025.10.0 版本！\n\n## :hammer: 库工程\n\n* 为 Scikit-learn* 扩展包添加了对 Scikit-learn 1.8 的支持\n\n## :rotating_light: 新特性\n\n* 引入了新的 Scikit-learn* 扩展功能：\n  * `DummyRegressor` 估计器\n\n## :beetle: 错误修复\n\n* 修复了在单类别数据上调用森林分类器时出现的错误\n* 修复了原始增量线性回归中的问题\n\n## 致谢\n\n感谢所有帮助我们实现 2025.10.0 版本发布的朋友们！\n\n@Alexsandruss、@Alexandr-Solovev、@Vika-F、@david-cortes-intel、@icfaust、@napetrov、@maria-Petrova、@homksei、@ahuber21、@ethanglaser、@razdoburdin、@avolkov-intel、@yuejiaointel、@DDJHB、@kjackiew、@richardnorth3\n\n**完整变更日志**：https:\u002F\u002Fgithub.com\u002Fuxlfoundation\u002Fscikit-learn-intelex\u002Fcompare\u002F2025.9.0...2025.10.0","2025-12-10T15:38:28",{"id":187,"version":188,"summary_zh":189,"released_at":190},280529,"2025.9.0","Scikit-learn* 扩展很荣幸地推出 2025.9.0 版本！\n\n## :rotating_light: 新特性\n\n* 引入了 Scikit-learn* 扩展的新功能：\n  * 在 `kNN` 搜索中启用了 SPMD API 支持\n  * 在 `PCA`、`EmpiricialCovariance` 及其增量变体中启用了数组 API 支持\n\n## :beetle: 错误修复\n\n* 修复了使用 GPU 数组时决策函数的错误\n* 修复了不可重用的 daal4py 对象被重复使用的问题\n* 防止逻辑回归在预测中出现 `inf` 值\n\n## 致谢\n\n感谢所有帮助我们实现 2025.9.0 版本发布的朋友们！\n\n@Alexsandruss、@Alexandr-Solovev、@Vika-F、@david-cortes-intel、@icfaust、@napetrov、@maria-Petrova、@homksei、@ahuber21、@ethanglaser、@razdoburdin、@avolkov-intel、@KateBlueSky、@yuejiaointel、@DDJHB、@kjackiew、@richardnorth3\n\n**完整变更日志**：https:\u002F\u002Fgithub.com\u002Fuxlfoundation\u002Fscikit-learn-intelex\u002Fcompare\u002F2025.8.0...2025.9.0","2025-10-27T11:54:55",{"id":192,"version":193,"summary_zh":194,"released_at":195},280530,"2025.8.0","Scikit-learn* 扩展很荣幸地推出 2025.8.0 版本！\n\n## :rotating_light: 新特性\n\n* 引入了 Scikit-learn* 扩展的新功能：\n  * 在 DBSCAN 中启用了数组 API 支持\n  * 在 `BasicStatistics`、`LinearRegression`、`Ridge` 算法及其增量变体中启用了数组 API 支持\n  * 添加了用于控制协方差和 PCA 使用批处理还是非批处理路径的参数\n  * 为 pytest 启用了通用的冗余级别参数\n\n## :beetle: 错误修复\n\n* 修复了不正确的类型转换和不匹配的操作符\n* 修复了逻辑回归正则化项被权重之和二次除的情况\n* 修复了将正则化传递给 scikit-learn 时的错误处理问题\n* GPU 版本的逻辑回归现在会返回正确形状的概率值\n\n## 致谢\n\n感谢所有帮助我们实现 2025.8.0 版本发布的朋友们！\n\n@Alexsandruss、@Alexandr-Solovev、@Vika-F、@david-cortes-intel、@icfaust、@napetrov、@maria-Petrova、@homksei、@ahuber21、@ethanglaser、@razdoburdin、@avolkov-intel、@KateBlueSky、@yuejiaointel、@DDJHB、@kjackiew、@richardnorth3\n\n## 新贡献者\n\n* @KateBlueSky 在 https:\u002F\u002Fgithub.com\u002Fuxlfoundation\u002Fscikit-learn-intelex\u002Fpull\u002F2640 中做出了首次贡献\n\n**完整变更日志**：https:\u002F\u002Fgithub.com\u002Fuxlfoundation\u002Fscikit-learn-intelex\u002Fcompare\u002F2025.7.0...2025.8.0","2025-08-20T08:09:24",{"id":197,"version":198,"summary_zh":199,"released_at":200},280531,"2025.7.0","Scikit-learn* 扩展很荣幸地推出 2025.7.0 版本！\n\n## :rotating_light: 新特性\n\n* 引入了 Scikit-learn* 扩展的新功能：\n  * 增加了对 sklearn 1.6 兼容性测试的支持\n  * 在 EmpiricalCovariance 和 PCA 算法中新增了 `grain_size` 超参数\n  * 支持将模型从 TreeLite 进行转换\n\n## :beetle: 错误修复\n\n* 修复了一些基础统计质量的小问题\n* 修正了 spmd 的策略变更\n* 修复了 Forest dpctl 预测队列的对齐问题\n* 修复了用于检查不同 oneAPI DMLL 库是否存在逻辑中的问题\n\n## 致谢\n\n感谢所有帮助我们实现 2025.7.0 版本发布的朋友们！\n\n@Alexsandruss、@Alexandr-Solovev、@Vika-F、@david-cortes-intel、@icfaust、@napetrov、@maria-Petrova、@homksei、@ahuber21、@ethanglaser、@razdoburdin、@avolkov-intel、@yuejiaointel\n\n**完整更新日志**：https:\u002F\u002Fgithub.com\u002Fuxlfoundation\u002Fscikit-learn-intelex\u002Fcompare\u002F2025.6.1...2025.7.0","2025-07-10T09:35:04",{"id":202,"version":203,"summary_zh":204,"released_at":205},280532,"2025.6.1","Scikit-learn* 扩展很荣幸地推出 2025.6.1 版本！\n\n## :rotating_light: 新功能\n\n* 引入了 Scikit-learn* 扩展的新功能：\n  * 模型构建者现在可以使用包含链接函数的 XGBoost 回归模型\n  * 提升了 XGBoost 在对象建模方面的兼容性\n  * 为逻辑回归模型构建器新增了一个带有 `.predict()` 方法的类\n\n## :beetle: 错误修复\n\n* 决策树相关错误修复\n* 修复了在使用 DPC 构建时强制 D4P 编译器切换到 ICX 的问题\n* 修复了对 sklearn 1.7 预发布版本的支持问题\n\n## 致谢\n\n感谢所有帮助我们实现 2025.6.1 版本发布的朋友们！\n\n@Alexsandruss、@Alexandr-Solovev、@Vika-F、@david-cortes-intel、@icfaust、@napetrov、@maria-Petrova、@homksei、@ahuber21、@ethanglaser、@razdoburdin、@avolkov-intel、@yuejiaointel\n\n**完整变更日志**：https:\u002F\u002Fgithub.com\u002Fuxlfoundation\u002Fscikit-learn-intelex\u002Fcompare\u002F2025.5.0...2025.6.1","2025-06-26T14:51:10",{"id":207,"version":208,"summary_zh":209,"released_at":210},280533,"2025.5.0","Scikit-learn* 扩展很荣幸地推出 2025.5.0 版本！\n\n## :rotating_light: 新特性\n\n* 引入了 Scikit-learn* 扩展的新功能：\n  * 为线性回归新增参数\n  * 加速了 sklearnex 的 `validate_data` 和 `_check_sample_weight` 对 array_api 输入的支持\n  * 模型构建器现在可以处理包含链接函数的 XGBoost 回归模型\n  * XGBoost 模型对象在转换为 daal4py 后不会被失效\n  * 逻辑回归模型构建器现提供带有 `.predict()` 方法的类\n\n## :beetle: 错误修复\n\n* 将决策树的 `.values` 属性规范化，以匹配 scikit-learn 的实现\n* 修复了 XGB 回归目标中 `base_score` 缩放不正确的问题\n* 修复了在 SYCL CPU 设备不可用时 csr k-Means `Init` 下载执行出现的问题\n\n## 致谢\n\n感谢所有帮助我们实现 2025.5.0 版本发布的朋友们！\n\n@Alexsandruss、@Alexandr-Solovev、@Vika-F、@david-cortes-intel、@icfaust、@napetrov、@maria-Petrova、@homksei、@ahuber21、@ethanglaser、@razdoburdin、@avolkov-intel、@yuejiaointel\n\n## 新贡献者\n\n* @tanannie22 在 https:\u002F\u002Fgithub.com\u002Fuxlfoundation\u002Fscikit-learn-intelex\u002Fpull\u002F2343 中做出了首次贡献\n\n**完整变更日志**：https:\u002F\u002Fgithub.com\u002Fuxlfoundation\u002Fscikit-learn-intelex\u002Fcompare\u002F2025.4.0...2025.5.0","2025-04-23T12:35:02",{"id":212,"version":213,"summary_zh":214,"released_at":215},280534,"2025.4.0","Scikit-learn* 扩展很荣幸地推出 2025.4.0 版本！\n\n## :rotating_light: 新功能\n\n* 引入了 Scikit-learn* 扩展的新功能：\n  * 通过添加可点击链接改进了帮助文档\n  * 增加了对 Python 3.13 的支持\n  * 增加了对 Scikit-learn 1.6 的支持\n\n## 致谢\n\n感谢所有帮助我们实现 2025.4.0 版本发布的朋友们！\n\n@Alexsandruss、@Alexandr-Solovev、@Vika-F、@david-cortes-intel、@icfaust、@napetrov、@maria-Petrova、@homksei、@ahuber21、@ethanglaser、@razdoburdin、@avolkov-intel、@yuejiaointel、\n\n**完整变更日志**：https:\u002F\u002Fgithub.com\u002Fuxlfoundation\u002Fscikit-learn-intelex\u002Fcompare\u002F2025.2.0...2025.4.0","2025-04-02T12:54:04",{"id":217,"version":218,"summary_zh":219,"released_at":220},280535,"2025.2.0","适用于 Scikit-learn* 的扩展很荣幸地推出 2025.2.0 版本！\n\n## :rotating_light: 新特性\n\n* 引入了 Intel® Extension for Scikit-learn* 的新功能：\n  * 在非正定半矩阵（PSD）系统上支持 GPU 上的线性回归\n  * 为 `IncrementalBasicStatistics`、`IncrementalEmpiricalCovariance` 和 `IncrementalPCA` 添加了序列化支持\n  * 将岭回归从预览阶段移出\n  * 禁用 k-Means（`n_clusters=1`）的补丁功能\n  * 添加了 `validate_data` 和 `_check_sample_weight` 的 sklearnex 版本\n  * 升级了针对欠定系统的 `IncrementalLinearRegression`\n  * 支持新的随机数生成器引擎\n\n## :beetle: 错误修复\n\n* 在无法使用 dpctl 时，启用了对 fp64 的正确 GPU 加速\n* 修复了在使用低精度队列时，针对非数组输入的 `to_table` 方法\n* 修复了增量主成分分析示例中的补丁逻辑\n\n## 致谢\n\n感谢所有帮助我们实现 2025.2.0 版本发布的朋友们！\n\n@Alexsandruss、@Alexandr-Solovev、@Vika-F、@david-cortes-intel、@icfaust、@napetrov、@maria-Petrova、@homksei、@ahuber21、@ethanglaser、@razdoburdin、@avolkov-intel、@yuejiaointel\n\n\n## 新贡献者\n\n* @yuejiaointel 在 https:\u002F\u002Fgithub.com\u002Fuxlfoundation\u002Fscikit-learn-intelex\u002Fpull\u002F2229 中做出了他们的首次贡献\n\n**完整变更日志**：https:\u002F\u002Fgithub.com\u002Fuxlfoundation\u002Fscikit-learn-intelex\u002Fcompare\u002F2025.1.0...2025.2.0","2025-02-24T16:58:28",{"id":222,"version":223,"summary_zh":224,"released_at":225},280536,"2025.1.0","Intel® Extension for Scikit-learn* is happy to introduce 2025.1.0 release! \r\n\r\n## :rotating_light: What's New\r\n\r\n* Introduced new Intel® Extension for Scikit-learn* functionality: \r\n  * Enabled accelerated Linear Regression for overdetermined systems\r\n  * Enabled hyperparameter support for Random Forest classifier inference\r\n  * Enabled serialization in `daal4py` algorithm classes\r\n\r\n## :beetle: Bug Fixes\r\n\r\n* Fixed int overflow in FTI model convertor\r\n* Updated ```BasicStatistics``` and ```IncrementalBasicStatistics``` to follow additional sklearn conventions\r\n* Fixed `n_jobs` support coverage to indirectly-supported oneDAL methods\r\n* Fixed KMeans ```score``` check in ```_onedal_*_supported``` and `n_jobs` support for ```score```\r\n* Corrected skips in design rule checks (```test_common.py```) caused by fragile `whitelist_to_blacklist`\r\n* Fixed  ```test_estimators[LogisticRegression()-check_estimators_unfitted]``` conformance for gpu support\r\n* Updated functional support fallback logic for a DPNP\u002FDPCTL ndarray inputs\r\n* Fixed an issue in aliased `_onedal_cpu_supported` and `_onedal_gpu_supported` in `fit_check_before_support_check`\r\n* Fixed logic of k-NN algos ```kneighbors()``` call when ```algorithm='brute'``` and fit with GPU\r\n\r\n## :hammer: Library Engineering\r\n\r\n* Added Python 3.13 support for Intel® Extension for Scikit-learn* packages\r\n* Added Sklearn 1.6 support for Intel® Extension for Scikit-learn* packages\r\n\r\n## Acknowledgements\r\nThanks to everyone who helped us make 2025.1.0 release possible!\r\n\r\n@Alexsandruss, @Alexandr-Solovev, @Vika-F, @david-cortes-intel, @icfaust, @napetrov, @maria-Petrova, @homksei, @ahuber21, @ethanglaser, @samir-nasibli, @olegkkruglov, @razdoburdin, @avolkov-intel, @md-shafiul-alam\r\n\r\n\r\n**Full Changelog**: https:\u002F\u002Fgithub.com\u002Fuxlfoundation\u002Fscikit-learn-intelex\u002Fcompare\u002F2025.0.0...2025.1.0","2025-01-17T12:04:12",{"id":227,"version":228,"summary_zh":229,"released_at":230},280537,"2025.0.0","Intel® Extension for Scikit-learn* is happy to introduce 2025.0.0 release! \r\n\r\n## :rotating_light: What's New\r\n\r\n* Introduced new Intel® Extension for Scikit-learn* functionality: \r\n  * Enabled functional support for Array API\r\n  * k-Means algorithm is moved out of preview namespace\r\n  * SHAP value support for XGBoost's binary classification models\r\n  * SPMD interfaces support: `IncrementalLinearRegression`, `IncrementalPCA`, `IncrementalEmpiricalCovariance`\r\n\r\n## :beetle: Bug Fixes\r\n\r\n* Fix issues with sklearn conformance for preview Ridge for 2024.6.0\r\n* Fix on preview ridge tests having too little error tolerance for coefficients assertions\r\n* Fix for Logistic Regression loss scaling\r\n* Fix to prevent `support_usm_ndarray` from changing queue if explicitly provided\r\n* Fix Multivariate Ridge Regression coefficients\r\n* Fix circular import in daal4py\u002Fsklearnex device_offloading\r\n* Align sklearnex `BasicStatistics._onedal_fit` with other algos\r\n\r\n## :x: Deprecation Notice\r\n\r\n* Removed Python 3.8 support\r\n\r\n## Acknowledgements\r\nThanks to everyone who helped us make 2025.0.0 release possible!\r\n\r\n@Alexsandruss, @Alexandr-Solovev, @Vika-F, @icfaust, @napetrov, @maria-Petrova, @ahuber21, @ethanglaser, @samir-nasibli, @aepanchi, @emmwalsh, @olegkkruglov, @razdoburdin, @avolkov-intel, @md-shafiul-alam, @david-cortes-intel  \r\n\r\n**Full Changelog**: https:\u002F\u002Fgithub.com\u002Fintel\u002Fscikit-learn-intelex\u002Fcompare\u002F2024.7.0...2025.0.0","2024-11-04T13:36:49",{"id":232,"version":233,"summary_zh":234,"released_at":235},280538,"2024.7.0","Intel® Extension for Scikit-learn* is happy to introduce 2024.7.0 release! \r\n\r\n## :rotating_light: What's New\r\n\r\n* Introduced new Intel® Extension for Scikit-learn* functionality: \r\n  * Sparse data support for `LogisticRegression`\r\n  * `Basic Statistic` API improvement\r\n  * Added `random_state` warning to SVM probability estimates\r\n  * Unified daal4py and sklearnex builds\r\n\r\n## :beetle: Bug Fixes\r\n\r\n* Fix issues with sklearn conformance for preview Ridge for 2024.6.0\r\n* Fix on preview ridge tests having too little error tolerance for coefficients assertions\r\n* Fix for Logistic Regression loss scaling\r\n* Fix to prevent `support_usm_ndarray` from changing queue if explicitly provided\r\n* Fix Multivariate Ridge Regression coefficients\r\n* Fix circular import in daal4py\u002Fsklearnex device_offloading\r\n* Align sklearnex `BasicStatistics._onedal_fit` with other algos\r\n\r\n## :x: Deprecation Notice\r\n\r\n* Removed Python 3.8 support\r\n\r\n## Acknowledgements\r\nThanks to everyone who helped us make 2024.7.0 release possible!\r\n\r\n@Alexsandruss, @Alexandr-Solovev, @Vika-F, @icfaust, @napetrov, @maria-Petrova, @ahuber21, @ethanglaser, @samir-nasibli, @aepanchi, @emmwalsh, @olegkkruglov, @razdoburdin, @avolkov-intel, @md-shafiul-alam\r\n\r\n**Full Changelog**: https:\u002F\u002Fgithub.com\u002Fintel\u002Fscikit-learn-intelex\u002Fcompare\u002F2024.6.0...2024.7.0","2024-09-18T12:49:48",{"id":237,"version":238,"summary_zh":239,"released_at":240},280539,"2024.6.0","Intel® Extension for Scikit-learn* is happy to introduce 2024.6.0 release! \r\n\r\n## :rotating_light: What's New\r\n\r\n* Introduced new Intel® Extension for Scikit-learn* functionality: \r\n  * `Incremental PCA` algorithm\r\n  * NumPy 2.0 support\r\n  * scikit-learn 1.5 support\r\n  * CSR data support in `Basic Statistics` algorithm\r\n\r\n## :beetle: Bug Fixes\r\n\r\n* Fix incorrect numpy to table conversion on Windows\r\n* Fix issues with dpnp\u002Fdpctl regressor score method\r\n\r\n## Acknowledgements\r\nThanks to everyone who helped us make 2024.6.0 release possible!\r\n\r\n@Alexsandruss, @Alexandr-Solovev, @Vika-F, @icfaust, @napetrov, @maria-Petrova, @ahuber21, @ethanglaser, @samir-nasibli, @aepanchi, @emmwalsh, @olegkkruglov, @razdoburdin, @avolkov-intel, @md-shafiul-alam\r\n\r\n**Full Changelog**: https:\u002F\u002Fgithub.com\u002Fintel\u002Fscikit-learn-intelex\u002Fcompare\u002F2024.5.0...2024.6.0","2024-08-13T15:40:01",{"id":242,"version":243,"summary_zh":244,"released_at":245},280540,"2024.5.0","Intel® Extension for Scikit-learn* is happy to introduce 2024.5.0 release! \r\n\r\n## :rotating_light: What's New\r\n\r\n* Introduced new Intel® Extension for Scikit-learn* functionality: \r\n  * `IncrementalLinearRegression` interface\r\n  * `IncrementalEmpiricalCovariance` interface to `patch_map`\r\n\r\n## :beetle: Bug Fixes\r\n\r\n* Fix dpnp\u002Fdpctl F-contiguous data processing\r\n\r\n## Acknowledgements\r\nThanks to everyone who helped us make 2024.5.0 release possible!\r\n\r\n@Alexsandruss, @Alexandr-Solovev, @Vika-F, @icfaust, @napetrov, @maria-Petrova, @ahuber21, @ethanglaser, @samir-nasibli, @aepanchi, @emmwalsh, @olegkkruglov, @razdoburdin, @avolkov-intel, @md-shafiul-alam\r\n\r\n**Full Changelog**: https:\u002F\u002Fgithub.com\u002Fintel\u002Fscikit-learn-intelex\u002Fcompare\u002F2024.4.0...2024.5.0","2024-07-02T10:42:09",{"id":247,"version":248,"summary_zh":249,"released_at":250},280541,"2024.4.0","Intel® Extension for Scikit-learn* is happy to introduce 2024.4.0 release! \r\n\r\n## :rotating_light: What's New\r\n\r\n* Introduced new Intel® Extension for Scikit-learn* functionality: \r\n  * `IncrementalBasicStatistics` interface\r\n  * Added `_n_inner_iter` attribute for Logistic Regression\r\n  * Added `assume_centered` capability to `EmpiricalCovariance`\r\n\r\n* Improved Intel® Extension for Scikit-learn* performance for the following algorithms:\r\n  * PCA\r\n\r\n## :beetle: Bug Fixes\r\n\r\n* Fix `sample_weight` check for `IncrementalBasicStatistics`\r\n* Fix dpnp\u002Fdpctl slowdown in `fit` method of neighbors algorithms\r\n\r\n## Acknowledgements\r\nThanks to everyone who helped us make 2024.4.0 release possible!\r\n\r\n@Alexsandruss, @Alexandr-Solovev, @Vika-F, @icfaust, @napetrov, @maria-Petrova, @ahuber21, @ethanglaser, @samir-nasibli, @aepanchi, @emmwalsh, @olegkkruglov, @razdoburdin, @avolkov-intel, @md-shafiul-alam\r\n\r\n**Full Changelog**: https:\u002F\u002Fgithub.com\u002Fintel\u002Fscikit-learn-intelex\u002Fcompare\u002F2024.3.0...2024.4.0","2024-05-16T14:22:44",{"id":252,"version":253,"summary_zh":254,"released_at":255},280542,"2024.3.0","Intel® Extension for Scikit-learn* is happy to introduce 2024.3.0 release! \r\n\r\n## :rotating_light: What's New\r\n\r\n* Introduced new Intel® Extension for Scikit-learn* functionality: \r\n  * `model_selection` in sklearnex namespace\r\n  *  SPMD backend library is separated from dpc backend\r\n  * PCA algorithm is moved out of preview namespace\r\n\r\n* Improved Intel® Extension for Scikit-learn* performance for the following algorithms:\r\n  * PCA\r\n\r\n## :beetle: Bug Fixes\r\n\r\n* Fix `test_patching` routines for intelex-only sklearnex estimators\r\n* Update sklearnex init based on SPMD backend changes\r\n* Fix import error by adding conditional check of `OFF_ONEDAL_IFACE` flag when importing onedal\r\n\r\n## :x: Deprecation Notice\r\n\r\n* Sklearn estimators in onedal4py `LinReg` and `k-Means` algorithms is deprecated for usage\r\n\r\n\r\n## Acknowledgements\r\nThanks to everyone who helped us make 2024.3.0 release possible!\r\n\r\n@Alexsandruss, @Alexandr-Solovev, @Vika-F, @icfaust, @napetrov, @ahuber21, @ethanglaser, @samir-nasibli, @aepanchi, @olegkkruglov, @razdoburdin, @maria-Petrova, @avolkov-intel, @md-shafiul-alam\r\n\r\n**Full Changelog**: https:\u002F\u002Fgithub.com\u002Fintel\u002Fscikit-learn-intelex\u002Fcompare\u002F2024.2.0...2024.3.0","2024-04-11T16:14:44",{"id":257,"version":258,"summary_zh":259,"released_at":260},280543,"2024.2.0","Intel® Extension for Scikit-learn* is happy to introduce 2024.2.0 release! \r\n\r\n## :rotating_light: What's New\r\n\r\n* Introduced new Intel(R) Extension for Scikit-learn* functionality: \r\n  * Incremental Covariance algorithm\r\n  * Logistic Regression algorithm is moved out of preview namespace\r\n  * SPMD interfaces support: Logistic Regression, Covariance\r\n\r\n## :hammer: Library Engineering\r\n\r\n* Enabled scikit-learn 1.4 support\r\n\r\n## :beetle: Bug Fixes\r\n\r\n* Adjusted `n_jobs` parameter setting\r\n* Updated DPCPP detection in setup\r\n* Fix of k-Means SPMD timeout\r\n* Correct disabling of CatBoost SHAP\r\n* Fix `LocalOutlierFactor` kneighbors method\r\n\r\n## Acknowledgements\r\nThanks to everyone who helped us make 2024.2.0 release possible! \r\n\r\n@Alexsandruss, @icfaust, @napetrov, @ahuber21, @ethanglaser, @samir-nasibli, @aepanchi, @olegkkruglov, @razdoburdin,  @maria-Petrova, @avolkov-intel\r\n\r\n**Full Changelog**: https:\u002F\u002Fgithub.com\u002Fintel\u002Fscikit-learn-intelex\u002Fcompare\u002F2024.1.0...2024.2.0","2024-04-02T19:33:18",{"id":262,"version":263,"summary_zh":264,"released_at":265},280544,"2024.1.0","Intel® Extension for Scikit-learn* is happy to introduce 2024.1.0 release! \r\n\r\n## :rotating_light: What's New\r\n\r\n* New Intel® Extension for Scikit-learn* functionality: \r\n  * SHAP support for symmetric CatBoost models\r\n  * Added oneDAL LinReg and Covariance hyperparameters API\r\n  * Added LogisticRegression interface to the preview section\r\n  * Initial support of `n_jobs` parameter\r\n\r\n## Acknowledgements\r\nThanks to everyone who helped us make 2024.1.0 release possible! \r\n\r\n@Alexsandruss, @icfaust, @napetrov, @ahuber21, @ethanglaser, @samir-nasibli, @aepanchi, @olegkkruglov, @razdoburdin, @KulikovNikita,  @maria-Petrova, @avolkov-intel\r\n\r\n**Full Changelog**: https:\u002F\u002Fgithub.com\u002Fintel\u002Fscikit-learn-intelex\u002Fcompare\u002F2024.0.1...2024.1.0","2024-01-24T21:51:51",{"id":267,"version":268,"summary_zh":269,"released_at":270},280545,"2024.0.1","Intel® Extension for Scikit-learn* is happy to introduce 2024.0.1 release! \r\n\r\n## :rotating_light: What's New\r\n\r\n* New Intel(R) Extension for Scikit-learn* functionality: \r\n  * Linear Regression and ensemble algorithms are moved out of preview namespace\r\n* New Model Builders functionality:\r\n  * SHAP calculation is added to GBT regression\r\n\r\n## :hammer: Library Engineering\r\n\r\n* Added Python 3.12 support for daal4py and Intel(R) Extension for Scikit-learn* packages\r\n\r\n## :books: Support Materials\r\n\r\n[Faster XGBoost*, LightGBM, and CatBoost Inference on the CPU](https:\u002F\u002Fwww.intel.com\u002Fcontent\u002Fwww\u002Fus\u002Fen\u002Fdeveloper\u002Farticles\u002Ftechnical\u002Ffaster-xgboost-light-gbm-catboost-inference-on-cpu.html#gs.1m2dxh)\r\n[PS-S3-Ep23-with-scikit-learn-intelex](https:\u002F\u002Fwww.kaggle.com\u002Fcode\u002Fnapetrov\u002Fps-s3-ep23-with-scikit-learn-intelex)\r\n[pss3e23 fusion_model with scikit-learn-intelex](https:\u002F\u002Fwww.kaggle.com\u002Fcode\u002Fnapetrov\u002Fpss3e23-fusion-model-with-scikit-learn-intelex)\r\n[PS S3E25: Faster regression tuning with sklearnex](https:\u002F\u002Fwww.kaggle.com\u002Fcode\u002Falex97andreev\u002Fps-s3e25-faster-regression-tuning-with-sklearnex)\r\n\r\n\r\n## :twisted_rightwards_arrows: Adoption\r\n\r\n[TPOT2 AutoML  integration](https:\u002F\u002Fgithub.com\u002FEpistasisLab\u002Ftpot2\u002Fpull\u002F102)\r\n\r\n## Acknowledgements\r\nThanks to everyone who helped us make 2024.0.1 release possible! \r\n\r\n@Alexsandruss, @icfaust, @napetrov, @ahuber21, @ethanglaser, @samir-nasibli, @aepanchi, @olegkkruglov, @razdoburdin, @KulikovNikita,  @maria-Petrova, @avolkov-intel\r\n","2023-11-30T17:53:01"]