[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"similar-josStorer--RWKV-Runner":3,"tool-josStorer--RWKV-Runner":64},[4,17,27,35,43,56],{"id":5,"name":6,"github_repo":7,"description_zh":8,"stars":9,"difficulty_score":10,"last_commit_at":11,"category_tags":12,"status":16},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。",162132,3,"2026-04-05T11:01:52",[13,14,15],"开发框架","图像","Agent","ready",{"id":18,"name":19,"github_repo":20,"description_zh":21,"stars":22,"difficulty_score":23,"last_commit_at":24,"category_tags":25,"status":16},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",138956,2,"2026-04-05T11:33:21",[13,15,26],"语言模型",{"id":28,"name":29,"github_repo":30,"description_zh":31,"stars":32,"difficulty_score":23,"last_commit_at":33,"category_tags":34,"status":16},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。",107662,"2026-04-03T11:11:01",[13,14,15],{"id":36,"name":37,"github_repo":38,"description_zh":39,"stars":40,"difficulty_score":23,"last_commit_at":41,"category_tags":42,"status":16},3704,"NextChat","ChatGPTNextWeb\u002FNextChat","NextChat 是一款轻量且极速的 AI 助手，旨在为用户提供流畅、跨平台的大模型交互体验。它完美解决了用户在多设备间切换时难以保持对话连续性，以及面对众多 AI 模型不知如何统一管理的痛点。无论是日常办公、学习辅助还是创意激发，NextChat 都能让用户随时随地通过网页、iOS、Android、Windows、MacOS 或 Linux 端无缝接入智能服务。\n\n这款工具非常适合普通用户、学生、职场人士以及需要私有化部署的企业团队使用。对于开发者而言，它也提供了便捷的自托管方案，支持一键部署到 Vercel 或 Zeabur 等平台。\n\nNextChat 的核心亮点在于其广泛的模型兼容性，原生支持 Claude、DeepSeek、GPT-4 及 Gemini Pro 等主流大模型，让用户在一个界面即可自由切换不同 AI 能力。此外，它还率先支持 MCP（Model Context Protocol）协议，增强了上下文处理能力。针对企业用户，NextChat 提供专业版解决方案，具备品牌定制、细粒度权限控制、内部知识库整合及安全审计等功能，满足公司对数据隐私和个性化管理的高标准要求。",87618,"2026-04-05T07:20:52",[13,26],{"id":44,"name":45,"github_repo":46,"description_zh":47,"stars":48,"difficulty_score":23,"last_commit_at":49,"category_tags":50,"status":16},2268,"ML-For-Beginners","microsoft\u002FML-For-Beginners","ML-For-Beginners 是由微软推出的一套系统化机器学习入门课程，旨在帮助零基础用户轻松掌握经典机器学习知识。这套课程将学习路径规划为 12 周，包含 26 节精炼课程和 52 道配套测验，内容涵盖从基础概念到实际应用的完整流程，有效解决了初学者面对庞大知识体系时无从下手、缺乏结构化指导的痛点。\n\n无论是希望转型的开发者、需要补充算法背景的研究人员，还是对人工智能充满好奇的普通爱好者，都能从中受益。课程不仅提供了清晰的理论讲解，还强调动手实践，让用户在循序渐进中建立扎实的技能基础。其独特的亮点在于强大的多语言支持，通过自动化机制提供了包括简体中文在内的 50 多种语言版本，极大地降低了全球不同背景用户的学习门槛。此外，项目采用开源协作模式，社区活跃且内容持续更新，确保学习者能获取前沿且准确的技术资讯。如果你正寻找一条清晰、友好且专业的机器学习入门之路，ML-For-Beginners 将是理想的起点。",84991,"2026-04-05T10:45:23",[14,51,52,53,15,54,26,13,55],"数据工具","视频","插件","其他","音频",{"id":57,"name":58,"github_repo":59,"description_zh":60,"stars":61,"difficulty_score":10,"last_commit_at":62,"category_tags":63,"status":16},3128,"ragflow","infiniflow\u002Fragflow","RAGFlow 是一款领先的开源检索增强生成（RAG）引擎，旨在为大语言模型构建更精准、可靠的上下文层。它巧妙地将前沿的 RAG 技术与智能体（Agent）能力相结合，不仅支持从各类文档中高效提取知识，还能让模型基于这些知识进行逻辑推理和任务执行。\n\n在大模型应用中，幻觉问题和知识滞后是常见痛点。RAGFlow 通过深度解析复杂文档结构（如表格、图表及混合排版），显著提升了信息检索的准确度，从而有效减少模型“胡编乱造”的现象，确保回答既有据可依又具备时效性。其内置的智能体机制更进一步，使系统不仅能回答问题，还能自主规划步骤解决复杂问题。\n\n这款工具特别适合开发者、企业技术团队以及 AI 研究人员使用。无论是希望快速搭建私有知识库问答系统，还是致力于探索大模型在垂直领域落地的创新者，都能从中受益。RAGFlow 提供了可视化的工作流编排界面和灵活的 API 接口，既降低了非算法背景用户的上手门槛，也满足了专业开发者对系统深度定制的需求。作为基于 Apache 2.0 协议开源的项目，它正成为连接通用大模型与行业专有知识之间的重要桥梁。",77062,"2026-04-04T04:44:48",[15,14,13,26,54],{"id":65,"github_repo":66,"name":67,"description_en":68,"description_zh":69,"ai_summary_zh":69,"readme_en":70,"readme_zh":71,"quickstart_zh":72,"use_case_zh":73,"hero_image_url":74,"owner_login":75,"owner_name":76,"owner_avatar_url":77,"owner_bio":78,"owner_company":79,"owner_location":79,"owner_email":80,"owner_twitter":76,"owner_website":79,"owner_url":81,"languages":82,"stars":121,"forks":122,"last_commit_at":123,"license":124,"difficulty_score":23,"env_os":125,"env_gpu":126,"env_ram":127,"env_deps":128,"category_tags":138,"github_topics":139,"view_count":146,"oss_zip_url":79,"oss_zip_packed_at":79,"status":16,"created_at":147,"updated_at":148,"faqs":149,"releases":195},256,"josStorer\u002FRWKV-Runner","RWKV-Runner","A RWKV management and startup tool, full automation, only 8MB. And provides an interface compatible with the OpenAI API. RWKV is a large language model that is fully open source and available for commercial use.","RWKV-Runner 是一个轻量级（仅约 8MB）的开源工具，专为简化 RWKV 大语言模型的部署与使用而设计。它通过全自动化的流程，让用户无需复杂配置即可一键启动和管理 RWKV 模型。RWKV 本身是一个完全开源、可商用的大语言模型，而 RWKV-Runner 进一步降低了它的使用门槛。\n\n该工具特别适合希望本地运行大模型但缺乏深度技术背景的开发者、研究人员或技术爱好者。普通用户也能借助其图形界面轻松上手。对于已有 ChatGPT 客户端的用户，RWKV-Runner 提供了兼容 OpenAI API 的接口，意味着现有客户端可直接调用 RWKV 模型，无缝切换。\n\n技术上，RWKV-Runner 支持前后端分离部署，既可作为完整桌面应用使用，也可仅部署后端服务供远程调用。默认启用自定义 CUDA 内核加速，在提升推理速度的同时显著降低显存占用。此外，项目还提供了详细的部署示例和参数调优建议，兼顾易用性与灵活性。","\u003Cp align=\"center\">\n    \u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002FjosStorer_RWKV-Runner_readme_3ba43027b4be.png\">\n\u003C\u002Fp>\n\n\u003Ch1 align=\"center\">RWKV Runner\u003C\u002Fh1>\n\n\u003Cdiv align=\"center\">\n\nThis project aims to eliminate the barriers of using large language models by automating everything for you. All you\nneed is a lightweight executable program of just a few megabytes. Additionally, this project provides an interface\ncompatible with the OpenAI API, which means that every ChatGPT client is an RWKV client.\n\n[![license][license-image]][license-url]\n[![release][release-image]][release-url]\n[![py-version][py-version-image]][py-version-url]\n\nEnglish | [简体中文](README_ZH.md) | [日本語](README_JA.md)\n\n### Install\n\n[![Windows][Windows-image]][Windows-url]\n[![MacOS][MacOS-image]][MacOS-url]\n[![Linux][Linux-image]][Linux-url]\n\n[FAQs](https:\u002F\u002Fgithub.com\u002FjosStorer\u002FRWKV-Runner\u002Fwiki\u002FFAQs) | [Preview](#Preview) | [Download][download-url] | [Simple Deploy Example](#Simple-Deploy-Example) | [Server Deploy Examples](https:\u002F\u002Fgithub.com\u002FjosStorer\u002FRWKV-Runner\u002Ftree\u002Fmaster\u002Fdeploy-examples) | [MIDI Hardware Input](#MIDI-Input)\n\n[license-image]: http:\u002F\u002Fimg.shields.io\u002Fbadge\u002Flicense-MIT-blue.svg\n\n[license-url]: https:\u002F\u002Fgithub.com\u002FjosStorer\u002FRWKV-Runner\u002Fblob\u002Fmaster\u002FLICENSE\n\n[release-image]: https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Frelease\u002FjosStorer\u002FRWKV-Runner.svg\n\n[release-url]: https:\u002F\u002Fgithub.com\u002FjosStorer\u002FRWKV-Runner\u002Freleases\u002Flatest\n\n[py-version-image]: https:\u002F\u002Fimg.shields.io\u002Fpypi\u002Fpyversions\u002Ffastapi.svg\n\n[py-version-url]: https:\u002F\u002Fgithub.com\u002FjosStorer\u002FRWKV-Runner\u002Ftree\u002Fmaster\u002Fbackend-python\n\n[download-url]: https:\u002F\u002Fgithub.com\u002FjosStorer\u002FRWKV-Runner\u002Freleases\n\n[Windows-image]: https:\u002F\u002Fimg.shields.io\u002Fbadge\u002F-Windows-blue?logo=windows\n\n[Windows-url]: https:\u002F\u002Fgithub.com\u002FjosStorer\u002FRWKV-Runner\u002Fblob\u002Fmaster\u002Fbuild\u002Fwindows\u002FReadme_Install.txt\n\n[MacOS-image]: https:\u002F\u002Fimg.shields.io\u002Fbadge\u002F-MacOS-black?logo=apple\n\n[MacOS-url]: https:\u002F\u002Fgithub.com\u002FjosStorer\u002FRWKV-Runner\u002Fblob\u002Fmaster\u002Fbuild\u002Fdarwin\u002FReadme_Install.txt\n\n[Linux-image]: https:\u002F\u002Fimg.shields.io\u002Fbadge\u002F-Linux-black?logo=linux\n\n[Linux-url]: https:\u002F\u002Fgithub.com\u002FjosStorer\u002FRWKV-Runner\u002Fblob\u002Fmaster\u002Fbuild\u002Flinux\u002FReadme_Install.txt\n\n\u003C\u002Fdiv>\n\n## Tips\n\n- You can deploy [backend-python](.\u002Fbackend-python\u002F) on a server and use this program as a client only. Fill in\n  your server address in the Settings `API URL`.\n\n- If you are deploying and providing public services, please limit the request size through API gateway to prevent\n  excessive resource usage caused by submitting overly long prompts. Additionally, please restrict the upper limit of\n  requests' max_tokens based on your actual\n  situation: https:\u002F\u002Fgithub.com\u002FjosStorer\u002FRWKV-Runner\u002Fblob\u002Fmaster\u002Fbackend-python\u002Futils\u002Frwkv.py#L567, the default is set\n  as le=102400, which may result in significant resource consumption for individual responses in extreme cases.\n\n- Default configs has enabled custom CUDA kernel acceleration, which is much faster and consumes much less VRAM. If you\n  encounter possible compatibility issues (output garbled), go to the Configs page and turn\n  off `Use Custom CUDA kernel to Accelerate`, or try to upgrade your gpu driver.\n\n- If Windows Defender claims this is a virus, you can try\n  downloading [v1.3.7_win.zip](https:\u002F\u002Fgithub.com\u002FjosStorer\u002FRWKV-Runner\u002Freleases\u002Fdownload\u002Fv1.3.7\u002FRWKV-Runner_win.zip)\n  and letting it update automatically to the latest version, or add it to the trusted\n  list (`Windows Security` -> `Virus & threat protection` -> `Manage settings` -> `Exclusions` -> `Add or remove exclusions` -> `Add an exclusion` -> `Folder` -> `RWKV-Runner`).\n\n- For different tasks, adjusting API parameters can achieve better results. For example, for translation tasks, you can\n  try setting Temperature to 1 and Top_P to 0.3.\n\n## Features\n\n- RWKV model management and one-click startup.\n- Front-end and back-end separation, if you don't want to use the client, also allows for separately deploying the\n  front-end service, or the back-end inference service, or the back-end inference service with a WebUI.\n  [Simple Deploy Example](#Simple-Deploy-Example) | [Server Deploy Examples](https:\u002F\u002Fgithub.com\u002FjosStorer\u002FRWKV-Runner\u002Ftree\u002Fmaster\u002Fdeploy-examples)\n- Compatible with the OpenAI API, making every ChatGPT client an RWKV client. After starting the model,\n  open http:\u002F\u002F127.0.0.1:8000\u002Fdocs to view more details.\n- Automatic dependency installation, requiring only a lightweight executable program.\n- Pre-set multi-level VRAM configs, works well on almost all computers. In Configs page, switch Strategy to WebGPU, it\n  can also run on AMD, Intel, and other graphics cards.\n- User-friendly chat, completion, and composition interaction interface included. Also supports chat presets, attachment\n  uploads, MIDI hardware input, and track editing.\n  [Preview](#Preview) | [MIDI Hardware Input](#MIDI-Input)\n- Built-in WebUI option, one-click start of Web service, sharing your hardware resources.\n- Easy-to-understand and operate parameter configuration, along with various operation guidance prompts.\n- Built-in model conversion tool.\n- Built-in download management and remote model inspection.\n- Built-in one-click LoRA Finetune. (Windows Only)\n- Can also be used as an OpenAI ChatGPT, GPT-Playground, Ollama and more clients. (Fill in the API URL and API Key in\n  Settings page)\n- Multilingual localization.\n- Theme switching.\n- Automatic updates.\n\n## Simple Deploy Example\n\n```bash\ngit clone https:\u002F\u002Fgithub.com\u002FjosStorer\u002FRWKV-Runner\n\n# Then\ncd RWKV-Runner\npython .\u002Fbackend-python\u002Fmain.py #The backend inference service has been started, request \u002Fswitch-model API to load the model, refer to the API documentation: http:\u002F\u002F127.0.0.1:8000\u002Fdocs\n\n# Or\ncd RWKV-Runner\u002Ffrontend\nnpm ci\nnpm run build #Compile the frontend\ncd ..\npython .\u002Fbackend-python\u002Fwebui_server.py #Start the frontend service separately\n# Or\npython .\u002Fbackend-python\u002Fmain.py --webui #Start the frontend and backend service at the same time\n\n# Help Info\npython .\u002Fbackend-python\u002Fmain.py -h\n```\n\n## API Concurrency Stress Testing\n\n```bash\nab -p body.json -T application\u002Fjson -c 20 -n 100 -l http:\u002F\u002F127.0.0.1:8000\u002Fchat\u002Fcompletions\n```\n\nbody.json:\n\n```json\n{\n  \"messages\": [\n    {\n      \"role\": \"user\",\n      \"content\": \"Hello\"\n    }\n  ]\n}\n```\n\n## Embeddings API Example\n\nNote: v1.4.0 has improved the quality of embeddings API. The generated results are not compatible\nwith previous versions. If you are using embeddings API to generate knowledge bases or similar, please regenerate.\n\nIf you are using langchain, just use `OpenAIEmbeddings(openai_api_base=\"http:\u002F\u002F127.0.0.1:8000\", openai_api_key=\"sk-\")`\n\n```python\nimport numpy as np\nimport requests\n\n\ndef cosine_similarity(a, b):\n    return np.dot(a, b) \u002F (np.linalg.norm(a) * np.linalg.norm(b))\n\n\nvalues = [\n    \"I am a girl\",\n    \"我是个女孩\",\n    \"私は女の子です\",\n    \"广东人爱吃福建人\",\n    \"我是个人类\",\n    \"I am a human\",\n    \"that dog is so cute\",\n    \"私はねこむすめです、にゃん♪\",\n    \"宇宙级特大事件！号外号外！\"\n]\n\nembeddings = []\nfor v in values:\n    r = requests.post(\"http:\u002F\u002F127.0.0.1:8000\u002Fembeddings\", json={\"input\": v})\n    embedding = r.json()[\"data\"][0][\"embedding\"]\n    embeddings.append(embedding)\n\ncompared_embedding = embeddings[0]\n\nembeddings_cos_sim = [cosine_similarity(compared_embedding, e) for e in embeddings]\n\nfor i in np.argsort(embeddings_cos_sim)[::-1]:\n    print(f\"{embeddings_cos_sim[i]:.10f} - {values[i]}\")\n```\n\n## MIDI Input\n\nTip: You can download https:\u002F\u002Fgithub.com\u002FjosStorer\u002Fsgm_plus and unzip it to the program's `assets\u002Fsound-font` directory\nto use it as an offline sound source. Please note that if you are compiling the program from source code, do not place\nit in the source code directory.\n\nIf you don't have a MIDI keyboard, you can use virtual MIDI input software like `Virtual Midi Controller 3 LE`, along\nwith [loopMIDI](https:\u002F\u002Fwww.tobias-erichsen.de\u002Fwp-content\u002Fuploads\u002F2020\u002F01\u002FloopMIDISetup_1_0_16_27.zip), to use a regular\ncomputer keyboard as MIDI input.\n\n### USB MIDI Connection\n\n- USB MIDI devices are plug-and-play, and you can select your input device in the Composition page\n- ![image](https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002FjosStorer_RWKV-Runner_readme_5fe076a1fd35.png)\n\n### Mac MIDI Bluetooth Connection\n\n- For Mac users who want to use Bluetooth input,\n  please install [Bluetooth MIDI Connect](https:\u002F\u002Fapps.apple.com\u002Fus\u002Fapp\u002Fbluetooth-midi-connect\u002Fid1108321791), then click\n  the tray icon to connect after launching,\n  afterwards, you can select your input device in the Composition page.\n- ![image](https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002FjosStorer_RWKV-Runner_readme_ecb7ec3a45f6.png)\n\n### Windows MIDI Bluetooth Connection\n\n- Windows seems to have implemented Bluetooth MIDI support only for UWP (Universal Windows Platform) apps. Therefore, it\n  requires multiple steps to establish a connection. We need to create a local virtual MIDI device and then launch a UWP\n  application. Through this UWP application, we will redirect Bluetooth MIDI input to the virtual MIDI device, and then\n  this software will listen to the input from the virtual MIDI device.\n- So, first, you need to\n  download [loopMIDI](https:\u002F\u002Fwww.tobias-erichsen.de\u002Fwp-content\u002Fuploads\u002F2020\u002F01\u002FloopMIDISetup_1_0_16_27.zip)\n  to create a virtual MIDI device. Click the plus sign in the bottom left corner to create the device.\n- ![image](https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002FjosStorer_RWKV-Runner_readme_6f2b5e975eae.png)\n- Next, you need to download [Bluetooth LE Explorer](https:\u002F\u002Fapps.microsoft.com\u002Fdetail\u002F9N0ZTKF1QD98) to discover and\n  connect to Bluetooth MIDI devices. Click \"Start\" to search for devices, and then click \"Pair\" to bind the MIDI device.\n- ![image](https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002FjosStorer_RWKV-Runner_readme_4f92796c98e8.png)\n- Finally, you need to install [MIDIberry](https:\u002F\u002Fapps.microsoft.com\u002Fdetail\u002F9N39720H2M05),\n  This UWP application can redirect Bluetooth MIDI input to the virtual MIDI device. After launching it, double-click\n  your actual Bluetooth MIDI device name in the input field, and in the output field, double-click the virtual MIDI\n  device name we created earlier.\n- ![image](https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002FjosStorer_RWKV-Runner_readme_25289140ef68.png)\n- Now, you can select the virtual MIDI device as the input in the Composition page. Bluetooth LE Explorer no longer\n  needs to run, and you can also close the loopMIDI window, it will run automatically in the background. Just keep\n  MIDIberry open.\n- ![image](https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002FjosStorer_RWKV-Runner_readme_3a0b7a1a91b0.png)\n\n## Related Repositories:\n\n- RWKV-5-World: https:\u002F\u002Fhuggingface.co\u002FBlinkDL\u002Frwkv-5-world\u002Ftree\u002Fmain\n- RWKV-4-World: https:\u002F\u002Fhuggingface.co\u002FBlinkDL\u002Frwkv-4-world\u002Ftree\u002Fmain\n- RWKV-4-Raven: https:\u002F\u002Fhuggingface.co\u002FBlinkDL\u002Frwkv-4-raven\u002Ftree\u002Fmain\n- ChatRWKV: https:\u002F\u002Fgithub.com\u002FBlinkDL\u002FChatRWKV\n- RWKV-LM: https:\u002F\u002Fgithub.com\u002FBlinkDL\u002FRWKV-LM\n- RWKV-LM-LoRA: https:\u002F\u002Fgithub.com\u002FBlealtan\u002FRWKV-LM-LoRA\n- RWKV-v5-lora: https:\u002F\u002Fgithub.com\u002FJL-er\u002FRWKV-v5-lora\n- MIDI-LLM-tokenizer: https:\u002F\u002Fgithub.com\u002Fbriansemrau\u002FMIDI-LLM-tokenizer\n- ai00_rwkv_server: https:\u002F\u002Fgithub.com\u002Fcgisky1980\u002Fai00_rwkv_server\n- rwkv.cpp: https:\u002F\u002Fgithub.com\u002FsaharNooby\u002Frwkv.cpp\n- web-rwkv-py: https:\u002F\u002Fgithub.com\u002Fcryscan\u002Fweb-rwkv-py\n- web-rwkv: https:\u002F\u002Fgithub.com\u002Fcryscan\u002Fweb-rwkv\n\n## Preview\n\n### Homepage\n\n![image](https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002FjosStorer_RWKV-Runner_readme_2e57c17f1fab.png)\n\n### Chat\n\n![image](https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002FjosStorer_RWKV-Runner_readme_e5378a3344dd.png)\n\n![image](https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002FjosStorer_RWKV-Runner_readme_869c4eef8c89.png)\n\n### Completion\n\n![image](https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002FjosStorer_RWKV-Runner_readme_11ea43678557.png)\n\n### Composition\n\nTip: You can download https:\u002F\u002Fgithub.com\u002FjosStorer\u002Fsgm_plus and unzip it to the program's `assets\u002Fsound-font` directory\nto use it as an offline sound source. Please note that if you are compiling the program from source code, do not place\nit in the source code directory.\n\n![image](https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002FjosStorer_RWKV-Runner_readme_244eef80c800.png)\n\n![image](https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002FjosStorer_RWKV-Runner_readme_3836e4ed88d7.png)\n\n### Configuration\n\n![image](https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002FjosStorer_RWKV-Runner_readme_d0f76b21be4c.png)\n\n### Model Management\n\n![image](https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002FjosStorer_RWKV-Runner_readme_0e1c7993b63d.png)\n\n### Download Management\n\n![image](https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002FjosStorer_RWKV-Runner_readme_02c50909779a.png)\n\n### LoRA Finetune\n\n![image](https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002FjosStorer_RWKV-Runner_readme_b01092c32fcc.png)\n\n### Settings\n\n![image](https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002FjosStorer_RWKV-Runner_readme_714d00085c47.png)\n","\u003Cp align=\"center\">\n    \u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002FjosStorer_RWKV-Runner_readme_3ba43027b4be.png\">\n\u003C\u002Fp>\n\n\u003Ch1 align=\"center\">RWKV Runner\u003C\u002Fh1>\n\n\u003Cdiv align=\"center\">\n\n本项目旨在通过自动化一切操作，消除使用大语言模型（Large Language Model, LLM）的门槛。你只需要一个仅几兆字节的轻量级可执行程序。此外，本项目提供了与 OpenAI API 兼容的接口，这意味着每一个 ChatGPT 客户端都可以直接作为 RWKV 客户端使用。\n\n[![license][license-image]][license-url]\n[![release][release-image]][release-url]\n[![py-version][py-version-image]][py-version-url]\n\nEnglish | [简体中文](README_ZH.md) | [日本語](README_JA.md)\n\n### 安装\n\n[![Windows][Windows-image]][Windows-url]\n[![MacOS][MacOS-image]][MacOS-url]\n[![Linux][Linux-image]][Linux-url]\n\n[常见问题 FAQ](https:\u002F\u002Fgithub.com\u002FjosStorer\u002FRWKV-Runner\u002Fwiki\u002FFAQs) | [预览](#Preview) | [下载][download-url] | [简易部署示例](#Simple-Deploy-Example) | [服务器部署示例](https:\u002F\u002Fgithub.com\u002FjosStorer\u002FRWKV-Runner\u002Ftree\u002Fmaster\u002Fdeploy-examples) | [MIDI 硬件输入](#MIDI-Input)\n\n[license-image]: http:\u002F\u002Fimg.shields.io\u002Fbadge\u002Flicense-MIT-blue.svg\n\n[license-url]: https:\u002F\u002Fgithub.com\u002FjosStorer\u002FRWKV-Runner\u002Fblob\u002Fmaster\u002FLICENSE\n\n[release-image]: https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Frelease\u002FjosStorer\u002FRWKV-Runner.svg\n\n[release-url]: https:\u002F\u002Fgithub.com\u002FjosStorer\u002FRWKV-Runner\u002Freleases\u002Flatest\n\n[py-version-image]: https:\u002F\u002Fimg.shields.io\u002Fpypi\u002Fpyversions\u002Ffastapi.svg\n\n[py-version-url]: https:\u002F\u002Fgithub.com\u002FjosStorer\u002FRWKV-Runner\u002Ftree\u002Fmaster\u002Fbackend-python\n\n[download-url]: https:\u002F\u002Fgithub.com\u002FjosStorer\u002FRWKV-Runner\u002Freleases\n\n[Windows-image]: https:\u002F\u002Fimg.shields.io\u002Fbadge\u002F-Windows-blue?logo=windows\n\n[Windows-url]: https:\u002F\u002Fgithub.com\u002FjosStorer\u002FRWKV-Runner\u002Fblob\u002Fmaster\u002Fbuild\u002Fwindows\u002FReadme_Install.txt\n\n[MacOS-image]: https:\u002F\u002Fimg.shields.io\u002Fbadge\u002F-MacOS-black?logo=apple\n\n[MacOS-url]: https:\u002F\u002Fgithub.com\u002FjosStorer\u002FRWKV-Runner\u002Fblob\u002Fmaster\u002Fbuild\u002Fdarwin\u002FReadme_Install.txt\n\n[Linux-image]: https:\u002F\u002Fimg.shields.io\u002Fbadge\u002F-Linux-black?logo=linux\n\n[Linux-url]: https:\u002F\u002Fgithub.com\u002FjosStorer\u002FRWKV-Runner\u002Fblob\u002Fmaster\u002Fbuild\u002Flinux\u002FReadme_Install.txt\n\n\u003C\u002Fdiv>\n\n## 提示\n\n- 你可以将 [backend-python](.\u002Fbackend-python\u002F) 部署在服务器上，仅将本程序用作客户端。只需在设置中填写你的服务器地址到 `API URL` 即可。\n\n- 如果你正在部署并对外提供公共服务，请通过 API 网关限制请求大小，以防止因提交过长的提示（prompt）而导致资源过度消耗。此外，请根据实际情况限制请求中 `max_tokens` 的上限：https:\u002F\u002Fgithub.com\u002FjosStorer\u002FRWKV-Runner\u002Fblob\u002Fmaster\u002Fbackend-python\u002Futils\u002Frwkv.py#L567，默认值设为 `le=102400`，在极端情况下可能导致单次响应消耗大量资源。\n\n- 默认配置已启用自定义 CUDA kernel 加速，速度更快且显存（VRAM）占用更低。如果你遇到可能的兼容性问题（如输出乱码），请前往 Configs 页面关闭 `Use Custom CUDA kernel to Accelerate`（使用自定义 CUDA kernel 加速）选项，或尝试升级你的 GPU 驱动。\n\n- 如果 Windows Defender 报告此程序为病毒，你可以尝试下载 [v1.3.7_win.zip](https:\u002F\u002Fgithub.com\u002FjosStorer\u002FRWKV-Runner\u002Freleases\u002Fdownload\u002Fv1.3.7\u002FRWKV-Runner_win.zip)，让它自动更新至最新版本；或者将其添加到信任列表中（`Windows 安全中心` → `病毒和威胁防护` → `管理设置` → `排除项` → `添加或删除排除项` → `添加排除项` → `文件夹` → 选择 `RWKV-Runner` 文件夹）。\n\n- 针对不同任务，调整 API 参数可以获得更好的效果。例如，在翻译任务中，可以尝试将 Temperature 设为 1，Top_P 设为 0.3。\n\n## 功能特性\n\n- RWKV 模型管理与一键启动。\n- 前后端分离架构：如果你不想使用客户端，也可以单独部署前端服务、后端推理服务，或带 WebUI 的后端推理服务。  \n  [简易部署示例](#Simple-Deploy-Example) | [服务器部署示例](https:\u002F\u002Fgithub.com\u002FjosStorer\u002FRWKV-Runner\u002Ftree\u002Fmaster\u002Fdeploy-examples)\n- 兼容 OpenAI API，使每个 ChatGPT 客户端都能成为 RWKV 客户端。启动模型后，打开 http:\u002F\u002F127.0.0.1:8000\u002Fdocs 查看更多详情。\n- 自动安装依赖，仅需一个轻量级可执行程序。\n- 预设多级显存（VRAM）配置，几乎可在所有电脑上良好运行。在 Configs 页面将 Strategy 切换为 WebGPU，也可在 AMD、Intel 等显卡上运行。\n- 内置用户友好的聊天、补全和创作交互界面，支持聊天预设、附件上传、MIDI 硬件输入和音轨编辑。  \n  [预览](#Preview) | [MIDI 硬件输入](#MIDI-Input)\n- 内置 WebUI 选项，一键启动 Web 服务，共享你的硬件资源。\n- 参数配置清晰易懂，附带多种操作引导提示。\n- 内置模型转换工具。\n- 内置下载管理与远程模型检查功能。\n- 内置一键 LoRA 微调功能。（仅限 Windows）\n- 也可作为 OpenAI ChatGPT、GPT-Playground、Ollama 等客户端使用。（在设置页面填写 API URL 和 API Key 即可）\n- 多语言本地化支持。\n- 主题切换。\n- 自动更新。\n\n## 简易部署示例\n\n```bash\ngit clone https:\u002F\u002Fgithub.com\u002FjosStorer\u002FRWKV-Runner\n\n# 然后\ncd RWKV-Runner\npython .\u002Fbackend-python\u002Fmain.py # 后端推理服务已启动，调用 \u002Fswitch-model API 加载模型，参考 API 文档：http:\u002F\u002F127.0.0.1:8000\u002Fdocs\n\n# 或者\ncd RWKV-Runner\u002Ffrontend\nnpm ci\nnpm run build # 编译前端\ncd ..\npython .\u002Fbackend-python\u002Fwebui_server.py # 单独启动前端服务\n# 或者\npython .\u002Fbackend-python\u002Fmain.py --webui # 同时启动前后端服务\n\n# 帮助信息\npython .\u002Fbackend-python\u002Fmain.py -h\n```\n\n## API 并发压力测试\n\n```bash\nab -p body.json -T application\u002Fjson -c 20 -n 100 -l http:\u002F\u002F127.0.0.1:8000\u002Fchat\u002Fcompletions\n```\n\nbody.json:\n\n```json\n{\n  \"messages\": [\n    {\n      \"role\": \"user\",\n      \"content\": \"Hello\"\n    }\n  ]\n}\n```\n\n## Embeddings API 示例\n\n注意：v1.4.0 版本改进了 embeddings API 的质量。生成的结果与之前版本不兼容。如果你使用 embeddings API 生成知识库或类似内容，请重新生成。\n\n如果你使用 langchain，只需使用 `OpenAIEmbeddings(openai_api_base=\"http:\u002F\u002F127.0.0.1:8000\", openai_api_key=\"sk-\")`\n\n```python\nimport numpy as np\nimport requests\n\n\ndef cosine_similarity(a, b):\n    return np.dot(a, b) \u002F (np.linalg.norm(a) * np.linalg.norm(b))\n\n\nvalues = [\n    \"I am a girl\",\n    \"我是个女孩\",\n    \"私は女の子です\",\n    \"广东人爱吃福建人\",\n    \"我是个人类\",\n    \"I am a human\",\n    \"that dog is so cute\",\n    \"私はねこむすめです、にゃん♪\",\n    \"宇宙级特大事件！号外号外！\"\n]\n\nembeddings = []\nfor v in values:\n    r = requests.post(\"http:\u002F\u002F127.0.0.1:8000\u002Fembeddings\", json={\"input\": v})\n    embedding = r.json()[\"data\"][0][\"embedding\"]\n    embeddings.append(embedding)\n\ncompared_embedding = embeddings[0]\n\nembeddings_cos_sim = [cosine_similarity(compared_embedding, e) for e in embeddings]\n\nfor i in np.argsort(embeddings_cos_sim)[::-1]:\n    print(f\"{embeddings_cos_sim[i]:.10f} - {values[i]}\")\n```\n\n## MIDI 输入\n\n提示：你可以下载 https:\u002F\u002Fgithub.com\u002FjosStorer\u002Fsgm_plus 并将其解压到程序的 `assets\u002Fsound-font` 目录中，作为离线音源使用。请注意，如果你是从源代码编译程序，请不要将其放在源代码目录中。\n\n如果你没有 MIDI 键盘，可以使用虚拟 MIDI 输入软件（如 `Virtual Midi Controller 3 LE`）配合 [loopMIDI](https:\u002F\u002Fwww.tobias-erichsen.de\u002Fwp-content\u002Fuploads\u002F2020\u002F01\u002FloopMIDISetup_1_0_16_27.zip)，将普通电脑键盘用作 MIDI 输入。\n\n### USB MIDI 连接\n\n- USB MIDI 设备即插即用，你可以在“作曲”页面中选择输入设备\n- ![image](https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002FjosStorer_RWKV-Runner_readme_5fe076a1fd35.png)\n\n### Mac MIDI 蓝牙连接\n\n- 对于希望使用蓝牙输入的 Mac 用户，\n  请安装 [Bluetooth MIDI Connect](https:\u002F\u002Fapps.apple.com\u002Fus\u002Fapp\u002Fbluetooth-midi-connect\u002Fid1108321791)，启动后点击系统托盘图标进行连接，\n  之后即可在“作曲”页面中选择输入设备。\n- ![image](https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002FjosStorer_RWKV-Runner_readme_ecb7ec3a45f6.png)\n\n### Windows MIDI 蓝牙连接\n\n- Windows 似乎仅对 UWP（通用 Windows 平台）应用实现了蓝牙 MIDI 支持。因此，建立连接需要多个步骤。我们需要创建一个本地虚拟 MIDI 设备，然后启动一个 UWP 应用程序。通过该 UWP 应用程序，将蓝牙 MIDI 输入重定向到虚拟 MIDI 设备，然后本软件监听来自该虚拟 MIDI 设备的输入。\n- 首先，你需要下载 [loopMIDI](https:\u002F\u002Fwww.tobias-erichsen.de\u002Fwp-content\u002Fuploads\u002F2020\u002F01\u002FloopMIDISetup_1_0_16_27.zip)\n  来创建虚拟 MIDI 设备。点击左下角的加号创建设备。\n- ![image](https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002FjosStorer_RWKV-Runner_readme_6f2b5e975eae.png)\n- 接下来，你需要下载 [Bluetooth LE Explorer](https:\u002F\u002Fapps.microsoft.com\u002Fdetail\u002F9N0ZTKF1QD98) 来发现并连接蓝牙 MIDI 设备。点击“Start”搜索设备，然后点击“Pair”绑定 MIDI 设备。\n- ![image](https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002FjosStorer_RWKV-Runner_readme_4f92796c98e8.png)\n- 最后，你需要安装 [MIDIberry](https:\u002F\u002Fapps.microsoft.com\u002Fdetail\u002F9N39720H2M05)，\n  这个 UWP 应用程序可以将蓝牙 MIDI 输入重定向到虚拟 MIDI 设备。启动后，在输入字段中双击你的实际蓝牙 MIDI 设备名称，在输出字段中双击我们之前创建的虚拟 MIDI 设备名称。\n- ![image](https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002FjosStorer_RWKV-Runner_readme_25289140ef68.png)\n- 现在，你可以在“作曲”页面中选择虚拟 MIDI 设备作为输入。Bluetooth LE Explorer 不再需要运行，你也可以关闭 loopMIDI 窗口，它会在后台自动运行。只需保持 MIDIberry 打开即可。\n- ![image](https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002FjosStorer_RWKV-Runner_readme_3a0b7a1a91b0.png)\n\n## 相关仓库：\n\n- RWKV-5-World: https:\u002F\u002Fhuggingface.co\u002FBlinkDL\u002Frwkv-5-world\u002Ftree\u002Fmain\n- RWKV-4-World: https:\u002F\u002Fhuggingface.co\u002FBlinkDL\u002Frwkv-4-world\u002Ftree\u002Fmain\n- RWKV-4-Raven: https:\u002F\u002Fhuggingface.co\u002FBlinkDL\u002Frwkv-4-raven\u002Ftree\u002Fmain\n- ChatRWKV: https:\u002F\u002Fgithub.com\u002FBlinkDL\u002FChatRWKV\n- RWKV-LM: https:\u002F\u002Fgithub.com\u002FBlinkDL\u002FRWKV-LM\n- RWKV-LM-LoRA: https:\u002F\u002Fgithub.com\u002FBlealtan\u002FRWKV-LM-LoRA\n- RWKV-v5-lora: https:\u002F\u002Fgithub.com\u002FJL-er\u002FRWKV-v5-lora\n- MIDI-LLM-tokenizer: https:\u002F\u002Fgithub.com\u002Fbriansemrau\u002FMIDI-LLM-tokenizer\n- ai00_rwkv_server: https:\u002F\u002Fgithub.com\u002Fcgisky1980\u002Fai00_rwkv_server\n- rwkv.cpp: https:\u002F\u002Fgithub.com\u002FsaharNooby\u002Frwkv.cpp\n- web-rwkv-py: https:\u002F\u002Fgithub.com\u002Fcryscan\u002Fweb-rwkv-py\n- web-rwkv: https:\u002F\u002Fgithub.com\u002Fcryscan\u002Fweb-rwkv\n\n## 预览\n\n### 首页\n\n![image](https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002FjosStorer_RWKV-Runner_readme_2e57c17f1fab.png)\n\n### 聊天\n\n![image](https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002FjosStorer_RWKV-Runner_readme_e5378a3344dd.png)\n\n![image](https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002FjosStorer_RWKV-Runner_readme_869c4eef8c89.png)\n\n### 补全\n\n![image](https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002FjosStorer_RWKV-Runner_readme_11ea43678557.png)\n\n### 作曲\n\n提示：你可以下载 https:\u002F\u002Fgithub.com\u002FjosStorer\u002Fsgm_plus 并将其解压到程序的 `assets\u002Fsound-font` 目录中，作为离线音源使用。请注意，如果你是从源代码编译程序，请不要将其放在源代码目录中。\n\n![image](https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002FjosStorer_RWKV-Runner_readme_244eef80c800.png)\n\n![image](https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002FjosStorer_RWKV-Runner_readme_3836e4ed88d7.png)\n\n### 配置\n\n![image](https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002FjosStorer_RWKV-Runner_readme_d0f76b21be4c.png)\n\n### 模型管理\n\n![image](https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002FjosStorer_RWKV-Runner_readme_0e1c7993b63d.png)\n\n### 下载管理\n\n![image](https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002FjosStorer_RWKV-Runner_readme_02c50909779a.png)\n\n### LoRA 微调\n\n![image](https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002FjosStorer_RWKV-Runner_readme_b01092c32fcc.png)\n\n### 设置\n\n![image](https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002FjosStorer_RWKV-Runner_readme_714d00085c47.png)","# RWKV-Runner 快速上手指南\n\n## 环境准备\n\n- **操作系统**：支持 Windows、macOS 和 Linux\n- **硬件要求**：\n  - 推荐 NVIDIA GPU（启用 CUDA 加速）\n  - 无独立显卡也可运行（自动切换至 CPU 或 WebGPU 模式，支持 AMD\u002FIntel 显卡）\n- **前置依赖**：\n  - 若从源码部署，需安装 Python 3.8+ 和 Node.js（仅前端构建需要）\n  - 官方提供免依赖的轻量级可执行程序（几 MB），无需手动安装依赖\n\n> 💡 提示：国内用户建议使用 GitHub Release 下载安装包，或配置镜像加速 `git clone`。\n\n## 安装步骤\n\n### 方式一：直接下载可执行程序（推荐）\n\n1. 访问 [Release 页面](https:\u002F\u002Fgithub.com\u002FjosStorer\u002FRWKV-Runner\u002Freleases)\n2. 根据系统下载对应版本：\n   - **Windows**：下载 `.exe` 或 `.zip` 文件\n   - **macOS**：下载 `.dmg` 文件\n   - **Linux**：下载 AppImage 或 tar.gz 包\n3. 解压后直接运行主程序（首次启动会自动安装所需依赖）\n\n> ⚠️ 若 Windows Defender 报毒，可将程序目录加入排除列表，或先下载 [v1.3.7_win.zip](https:\u002F\u002Fgithub.com\u002FjosStorer\u002FRWKV-Runner\u002Freleases\u002Fdownload\u002Fv1.3.7\u002FRWKV-Runner_win.zip) 再自动更新。\n\n### 方式二：从源码部署（适合开发者）\n\n```bash\ngit clone https:\u002F\u002Fgithub.com\u002FjosStorer\u002FRWKV-Runner\ncd RWKV-Runner\n```\n\n#### 启动后端服务（推理 API）\n\n```bash\npython .\u002Fbackend-python\u002Fmain.py\n```\n\n#### 启动带 WebUI 的完整服务\n\n```bash\n# 先构建前端\ncd frontend\nnpm ci\nnpm run build\ncd ..\n\n# 启动集成服务\npython .\u002Fbackend-python\u002Fmain.py --webui\n```\n\n服务启动后，默认访问地址为 `http:\u002F\u002F127.0.0.1:8000`。\n\n## 基本使用\n\n### 1. 本地使用图形界面\n- 启动程序后，在 **模型管理** 页面下载或导入 RWKV 模型（如 `RWKV-5-World`）\n- 点击 **一键启动** 加载模型\n- 切换到 **Chat**、**Completion** 或 **Composition** 页面即可开始交互\n\n### 2. 调用 OpenAI 兼容 API（最简示例）\n\n确保服务已运行（默认端口 8000），发送请求：\n\n```bash\ncurl http:\u002F\u002F127.0.0.1:8000\u002Fv1\u002Fchat\u002Fcompletions \\\n  -H \"Content-Type: application\u002Fjson\" \\\n  -d '{\n    \"model\": \"rwkv\",\n    \"messages\": [{\"role\": \"user\", \"content\": \"你好\"}]\n  }'\n```\n\n> ✅ 所有支持 OpenAI API 的客户端（如 ChatGPT 前端、LangChain 等）均可直接对接 RWKV-Runner。\n\n### 3. 使用 Embeddings API（示例）\n\n```python\nimport requests\n\nr = requests.post(\"http:\u002F\u002F127.0.0.1:8000\u002Fembeddings\", json={\"input\": \"我是人类\"})\nembedding = r.json()[\"data\"][0][\"embedding\"]\nprint(embedding)\n```\n\n---\n\n> 📌 默认已启用 CUDA 自定义内核加速（更快、更省显存）。若输出乱码，请在设置中关闭 **Use Custom CUDA kernel to Accelerate** 或升级显卡驱动。","某中小型跨境电商团队希望在内部客服系统中集成一个本地部署的智能问答模块，用于自动回复常见售后问题，但团队缺乏专职 AI 运维人员，且服务器资源有限。\n\n### 没有 RWKV-Runner 时\n- 需手动下载 RWKV 模型文件、配置 Python 环境、安装依赖库，过程繁琐且容易出错。\n- 启动推理服务需编写脚本并调试 CUDA 兼容性，非专业开发者难以独立完成。\n- 无法直接对接现有基于 OpenAI API 开发的前端客服界面，必须重写调用逻辑。\n- 模型参数（如 temperature、max_tokens）调整需修改代码或配置文件，响应业务需求慢。\n- 资源占用高，未启用优化内核时显存消耗大，老旧 GPU 服务器频繁崩溃。\n\n### 使用 RWKV-Runner 后\n- 下载 8MB 的可执行程序后一键启动，自动完成模型加载与服务初始化，无需命令行操作。\n- 内置兼容 OpenAI API 的接口，原有客服前端几乎零改动即可调用本地 RWKV 模型。\n- 提供图形化界面实时调整推理参数，运营人员可快速测试不同生成效果。\n- 默认启用自定义 CUDA 加速内核，在同款 GPU 上显存占用降低近 40%，服务更稳定。\n- 支持仅部署后端服务，前端通过配置 API 地址远程调用，便于灵活架构部署。\n\nRWKV-Runner 让非 AI 专业团队也能低成本、高效率地将开源大模型落地到实际业务中。","https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002FjosStorer_RWKV-Runner_4fa99135.png","josStorer","josc146","https:\u002F\u002Foss.gittoolsai.com\u002Favatars\u002FjosStorer_5add8cda.jpg","Game Developer",null,"josStorer@outlook.com","https:\u002F\u002Fgithub.com\u002FjosStorer",[83,87,91,95,99,103,107,111,115,118],{"name":84,"color":85,"percentage":86},"TypeScript","#3178c6",68.5,{"name":88,"color":89,"percentage":90},"Python","#3572A5",20.5,{"name":92,"color":93,"percentage":94},"Go","#00ADD8",7,{"name":96,"color":97,"percentage":98},"Ruby","#701516",1.3,{"name":100,"color":101,"percentage":102},"JavaScript","#f1e05a",1,{"name":104,"color":105,"percentage":106},"Shell","#89e051",0.6,{"name":108,"color":109,"percentage":110},"Batchfile","#C1F12E",0.4,{"name":112,"color":113,"percentage":114},"SCSS","#c6538c",0.2,{"name":116,"color":117,"percentage":114},"Dockerfile","#384d54",{"name":119,"color":120,"percentage":114},"Makefile","#427819",6287,598,"2026-04-05T09:54:29","MIT","Linux, macOS, Windows","推荐 NVIDIA GPU（支持 CUDA），启用自定义 CUDA 内核可显著减少显存占用并提升速度；也支持 AMD、Intel 等显卡（需在配置中切换 Strategy 为 WebGPU）；未明确要求最低显存，但提示可通过多级 VRAM 配置适配几乎所有电脑","未说明",{"notes":129,"python":130,"dependencies":131},"程序提供轻量级可执行文件（几 MB），自动处理依赖安装；默认启用自定义 CUDA 内核加速，若输出乱码可关闭该选项或升级显卡驱动；支持通过 OpenAI API 兼容方式调用；可在无客户端情况下单独部署后端服务；Windows Defender 可能误报病毒，建议添加信任目录；内置模型转换、LoRA 微调（仅 Windows）、MIDI 输入等功能","未明确说明具体版本，但后端位于 backend-python 目录，且依赖 FastAPI（根据 py-version badge 推测需 Python 3.7+）",[132,133,134,135,136,137],"torch","fastapi","uvicorn","numpy","requests","rwkv",[53,15,13,26,51],[137,140,141,142,143,144,145],"api","api-client","chatgpt","llm","tool","wails",9,"2026-03-27T02:49:30.150509","2026-04-06T07:13:45.840560",[150,155,160,165,170,175,180,185,190],{"id":151,"question_zh":152,"answer_zh":153,"source_url":154},806,"RWKV-Runner 是否支持 Linux 系统？","支持，但需要手动构建前端资源。进入 frontend 目录后执行以下命令：\n%cd \u002Fcontent\u002FRWKV-Runner\u002Ffrontend\n!npm ci\n!npm install -g typescript\n!npm run build\n然后返回上一级目录启动后端。若提示找不到 tsc，请确保已全局安装 TypeScript。","https:\u002F\u002Fgithub.com\u002FjosStorer\u002FRWKV-Runner\u002Fissues\u002F50",{"id":156,"question_zh":157,"answer_zh":158,"source_url":159},807,"在 Windows Server 2019 上训练时报错 'could not get distro \"Ubuntu\"'s state'，如何解决？","该错误通常是因为系统版本过低不支持 WSL2。Windows Server 2019 版本号需为 18362.1049 或更高（即 1903 及以上）才能使用 WSL2。当前版本 17763.107（1809）不支持，需重装更高版本的 Windows Server 才能启用 WSL2。","https:\u002F\u002Fgithub.com\u002FjosStorer\u002FRWKV-Runner\u002Fissues\u002F213",{"id":161,"question_zh":162,"answer_zh":163,"source_url":164},808,"提示“Python依赖缺失”，点击安装无效怎么办？","可能是 Python 3.10 安装目录不完整，缺少 include 和 Libs 目录。解决方法是：从其他完整安装的 Python 3.10 环境中复制这两个目录到当前 py310 目录下，再重新编译或重装依赖即可解决。","https:\u002F\u002Fgithub.com\u002FjosStorer\u002FRWKV-Runner\u002Fissues\u002F31",{"id":166,"question_zh":167,"answer_zh":168,"source_url":169},809,"训练时出现 'RuntimeError: Error building extension wkv_1024_bf16' 错误如何处理？","建议卸载并重装 WSL 发行版（如 Ubuntu）。执行 wsl --unregister Ubuntu 后重新安装，并确保以默认用户（非 root）运行。若仍失败，可尝试使用 sudo 权限安装相关依赖，或将环境部署在 root 用户下。","https:\u002F\u002Fgithub.com\u002FjosStorer\u002FRWKV-Runner\u002Fissues\u002F121",{"id":171,"question_zh":172,"answer_zh":173,"source_url":174},810,"1.3.4 版本点击“训练”按钮无反应怎么办？","请将 WSL 更新至最新版本。可通过 Microsoft Store 重新安装 WSL，或在命令行中运行 wsl.exe --update 命令完成更新，之后即可正常启动训练。","https:\u002F\u002Fgithub.com\u002FjosStorer\u002FRWKV-Runner\u002Fissues\u002F110",{"id":176,"question_zh":177,"answer_zh":178,"source_url":179},811,"如何在 TavernAI 或 SillyTavern 中调用 RWKV-Runner 的 API？","在 TavernAI\u002FSillyTavern 的设置中配置 API 地址为 RWKV-Runner 的本地地址（如 http:\u002F\u002F127.0.0.1:8000），并使用兼容的请求格式。注意：生成长回复时可能因超时先报错，但实际仍能收到完整结果；后续版本计划增加 models API 改进兼容性。","https:\u002F\u002Fgithub.com\u002FjosStorer\u002FRWKV-Runner\u002Fissues\u002F136",{"id":181,"question_zh":182,"answer_zh":183,"source_url":184},812,"RWKV-Runner 强制安装 PyTorch 1.13.1，能否使用其他版本（如 2.0.1+cu118）？","可以。RWKV-Runner 并不强制限定 PyTorch 版本。你可自行安装所需版本，例如：pip3 install torch torchvision torchaudio --index-url https:\u002F\u002Fdownload.pytorch.org\u002Fwhl\u002Fcu118。同时确保安装 requirements.txt 中列出的其他依赖（如 rwkv、langchain 等），无需修改源码。","https:\u002F\u002Fgithub.com\u002FjosStorer\u002FRWKV-Runner\u002Fissues\u002F128",{"id":186,"question_zh":187,"answer_zh":188,"source_url":189},813,"在 Linux（AMD 显卡）上遇到 '400 bad request' 和流被锁定错误怎么办？","建议使用 WebGPU 模式运行。首先用 convert_safetensors.py 将 .pth 模型转为 .st 格式，然后以如下命令启动：python3 .\u002Fbackend-python\u002Fmain.py --webgpu。接着调用 \u002Fswitch-model 接口，传入 .st 文件路径即可加载模型。","https:\u002F\u002Fgithub.com\u002FjosStorer\u002FRWKV-Runner\u002Fissues\u002F298",{"id":191,"question_zh":192,"answer_zh":193,"source_url":194},814,"使用 sample.jsonl 数据转换成功后，点击训练仍提示“请先转换数据”怎么办？","此问题可能与 WSL2 中 nvcc 和 gcc 版本不兼容有关。建议确保 nvcc 版本 ≥11.2 且 gcc ≤6。若环境复杂，推荐在干净的 WSL2 或新机器上部署，避免依赖冲突。","https:\u002F\u002Fgithub.com\u002FjosStorer\u002FRWKV-Runner\u002Fissues\u002F108",[196,201,206,211,216,221,226,231,236,241,246,251,256,261,266,271,276,281,286,291],{"id":197,"version":198,"summary_zh":199,"released_at":200},110046,"v1.9.10","## Changes\n\n- fixed the inference issue of RWKV GGUF model caused by the API changes after the update of llama.cpp in the previous version\n\nNote: If you encounter WebView2 crash issues, please try opening the Windows Settings, click on Apps, search for\nWebView2, click Modify -> Repair to update your WebView2 runtime.\n\n## Install\n\n- Windows: https:\u002F\u002Fgithub.com\u002FjosStorer\u002FRWKV-Runner\u002Fblob\u002Fmaster\u002Fbuild\u002Fwindows\u002FReadme_Install.txt\n- MacOS: https:\u002F\u002Fgithub.com\u002FjosStorer\u002FRWKV-Runner\u002Fblob\u002Fmaster\u002Fbuild\u002Fdarwin\u002FReadme_Install.txt\n- Linux: https:\u002F\u002Fgithub.com\u002FjosStorer\u002FRWKV-Runner\u002Fblob\u002Fmaster\u002Fbuild\u002Flinux\u002FReadme_Install.txt\n- Simple Deploy Example: https:\u002F\u002Fgithub.com\u002FjosStorer\u002FRWKV-Runner\u002Fblob\u002Fmaster\u002FREADME.md#simple-deploy-example\n- Server Deploy Examples: https:\u002F\u002Fgithub.com\u002FjosStorer\u002FRWKV-Runner\u002Ftree\u002Fmaster\u002Fdeploy-examples\n- Windows 7 Patches: https:\u002F\u002Fgithub.com\u002FjosStorer\u002Fwails\u002Freleases\u002Ftag\u002Fv2.9.2x\n","2026-02-01T08:32:25",{"id":202,"version":203,"summary_zh":204,"released_at":205},110047,"v1.9.9","## Changes\n\n- add search input to Models page\n- \u003Cimg width=\"600\" src=\"https:\u002F\u002Fgithub.com\u002Fuser-attachments\u002Fassets\u002F63459a32-4d80-4429-b8c3-73e0d3cba8a6\" \u002F>\n- add support for mermaid rendering\n- \u003Cimg width=\"600\" src=\"https:\u002F\u002Fgithub.com\u002Fuser-attachments\u002Fassets\u002Fb9a1a388-5d11-4898-9f24-b282caa12e6d\" \u002F>\n- improve ThinkComponent\n- remove the compatibility support for top-level await; now only browsers\u002Fwebviews with Chromium 89+ are supported\n- update manifest.json and defaultConfigs\n- small fixes\n\nNote: If you encounter WebView2 crash issues, please try opening the Windows Settings, click on Apps, search for\nWebView2, click Modify -> Repair to update your WebView2 runtime.\n\n## Install\n\n- Windows: https:\u002F\u002Fgithub.com\u002FjosStorer\u002FRWKV-Runner\u002Fblob\u002Fmaster\u002Fbuild\u002Fwindows\u002FReadme_Install.txt\n- MacOS: https:\u002F\u002Fgithub.com\u002FjosStorer\u002FRWKV-Runner\u002Fblob\u002Fmaster\u002Fbuild\u002Fdarwin\u002FReadme_Install.txt\n- Linux: https:\u002F\u002Fgithub.com\u002FjosStorer\u002FRWKV-Runner\u002Fblob\u002Fmaster\u002Fbuild\u002Flinux\u002FReadme_Install.txt\n- Simple Deploy Example: https:\u002F\u002Fgithub.com\u002FjosStorer\u002FRWKV-Runner\u002Fblob\u002Fmaster\u002FREADME.md#simple-deploy-example\n- Server Deploy Examples: https:\u002F\u002Fgithub.com\u002FjosStorer\u002FRWKV-Runner\u002Ftree\u002Fmaster\u002Fdeploy-examples\n- Windows 7 Patches: https:\u002F\u002Fgithub.com\u002FjosStorer\u002Fwails\u002Freleases\u002Ftag\u002Fv2.9.2x\n","2026-01-27T12:55:11",{"id":207,"version":208,"summary_zh":209,"released_at":210},110048,"v1.9.8","## Changes\n\n- disable auto throttling of @microsoft\u002Ffetch-event-source\n- bump precompiled llama.cpp vulkan\n- add `stop_token_ids` field to `\u002Fcompletions` and `\u002Fchat\u002Fcompletions`\n- allow stop sequences to accept multiple values or numeric token IDs, passed to the api server as arrays\n  \u003Cimg width=\"331\" height=\"170\" alt=\"Image\" src=\"https:\u002F\u002Fgithub.com\u002Fuser-attachments\u002Fassets\u002F3dcd7a8b-9503-4fc4-8f89-6b0b8e33e933\" \u002F>\n- update manifest.json and defaultConfigs\n- small fixes\n\nNote: If you encounter WebView2 crash issues, please try opening the Windows Settings, click on Apps, search for\nWebView2, click Modify -> Repair to update your WebView2 runtime.\n\n## Install\n\n- Windows: https:\u002F\u002Fgithub.com\u002FjosStorer\u002FRWKV-Runner\u002Fblob\u002Fmaster\u002Fbuild\u002Fwindows\u002FReadme_Install.txt\n- MacOS: https:\u002F\u002Fgithub.com\u002FjosStorer\u002FRWKV-Runner\u002Fblob\u002Fmaster\u002Fbuild\u002Fdarwin\u002FReadme_Install.txt\n- Linux: https:\u002F\u002Fgithub.com\u002FjosStorer\u002FRWKV-Runner\u002Fblob\u002Fmaster\u002Fbuild\u002Flinux\u002FReadme_Install.txt\n- Simple Deploy Example: https:\u002F\u002Fgithub.com\u002FjosStorer\u002FRWKV-Runner\u002Fblob\u002Fmaster\u002FREADME.md#simple-deploy-example\n- Server Deploy Examples: https:\u002F\u002Fgithub.com\u002FjosStorer\u002FRWKV-Runner\u002Ftree\u002Fmaster\u002Fdeploy-examples\n- Windows 7 Patches: https:\u002F\u002Fgithub.com\u002FjosStorer\u002Fwails\u002Freleases\u002Ftag\u002Fv2.9.2x\n","2026-01-25T07:18:15",{"id":212,"version":213,"summary_zh":214,"released_at":215},110049,"v1.9.7","## Changes\n\n- add extra vc++ installation guide\n- add support for REMI tokenizer and raw token input\n- allow prompt to be empty when using `\u002Fcompletions` api\n- bump precompiled llama.cpp vulkan\n- add modelName and date to screenshot\n- update python dependencies\n- update manifest.json and defaultConfigs\n- chores\n\nNote: If you encounter WebView2 crash issues, please try opening the Windows Settings, click on Apps, search for\nWebView2, click Modify -> Repair to update your WebView2 runtime.\n\n## Install\n\n- Windows: https:\u002F\u002Fgithub.com\u002FjosStorer\u002FRWKV-Runner\u002Fblob\u002Fmaster\u002Fbuild\u002Fwindows\u002FReadme_Install.txt\n- MacOS: https:\u002F\u002Fgithub.com\u002FjosStorer\u002FRWKV-Runner\u002Fblob\u002Fmaster\u002Fbuild\u002Fdarwin\u002FReadme_Install.txt\n- Linux: https:\u002F\u002Fgithub.com\u002FjosStorer\u002FRWKV-Runner\u002Fblob\u002Fmaster\u002Fbuild\u002Flinux\u002FReadme_Install.txt\n- Simple Deploy Example: https:\u002F\u002Fgithub.com\u002FjosStorer\u002FRWKV-Runner\u002Fblob\u002Fmaster\u002FREADME.md#simple-deploy-example\n- Server Deploy Examples: https:\u002F\u002Fgithub.com\u002FjosStorer\u002FRWKV-Runner\u002Ftree\u002Fmaster\u002Fdeploy-examples\n- Windows 7 Patches: https:\u002F\u002Fgithub.com\u002FjosStorer\u002Fwails\u002Freleases\u002Ftag\u002Fv2.9.2x\n","2025-08-20T09:49:04",{"id":217,"version":218,"summary_zh":219,"released_at":220},110050,"v1.9.6","## Changes\r\n\r\n### Llama.cpp support\r\n\r\n- Add llama.cpp support with pre-compiled Vulkan libraries for Windows that should work out-of-the-box with any modern GPU. Mac and Linux users still need to manually install llama-cpp-python. You can now use RWKV GGUF models as well as any other GGUF models such as DeepSeek, Qwen3, Gemma3, Phi4. You can select the llama.cpp tag in the Models page and download the required models with one click, or place downloaded GGUF models in the models directory for use.\r\n- \u003Cimg src=\"https:\u002F\u002Fgithub.com\u002Fuser-attachments\u002Fassets\u002F7ff56440-41cd-4ef2-8a63-b057061ddbf4\" width=\"512\"\u002F>\r\n- The software's preset configs have been streamlined and now include some GGUF format presets. You can click the reset button to fetch the latest presets.\r\n- \u003Cimg src=\"https:\u002F\u002Fgithub.com\u002Fuser-attachments\u002Fassets\u002Fb3203434-ccea-4043-8384-6cf412c37eb7\" width=\"256\"\u002F>\r\n- The RWKV-Runner Python server in llama.cpp mode has been optimized. After loading the model to GPU, the server process only occupies approximately 200MB of memory on Windows platform.\r\n- When server users call the `\u002Fswitch-model` API to load models, you only need to pass a file path ending with .gguf to the `model` field to use llama.cpp mode.\r\n\r\n### Features\r\n\r\n- llama.cpp support\r\n- \u003Cimg src=\"https:\u002F\u002Fgithub.com\u002Fuser-attachments\u002Fassets\u002F50de157f-16cb-4d86-bb25-a1f13e2a031f\" width=\"512\"\u002F>\r\n- Add a setting to save the full rwkv-runner client state, rather than just storing necessary settings. This option is enabled by default. You can disable it and restart the software to restore the previous version's behavior\r\n- \u003Cimg src=\"https:\u002F\u002Fgithub.com\u002Fuser-attachments\u002Fassets\u002F4c8c7b13-8d62-4ff0-ab0d-d06c40d95f58\" width=\"512\"\u002F>\r\n- add a share button to save your chat screenshot\r\n- \u003Cimg src=\"https:\u002F\u002Fgithub.com\u002Fuser-attachments\u002Fassets\u002F11533e20-836c-487f-b3ae-5cf7988f12bc\" width=\"512\"\u002F>\r\n\r\n### Improvements\r\n- reduce peak memory usage when loading rwkv7 in cuda mode\r\n- increase the maximum value of the top_k API parameter to 100\r\n- remove language tags in Models page, as all new models support global languages\r\n- remove useless\u002Fdisabled resources\r\n- other small improvements\r\n- You can run RWKV-Runner on Windows 7 by installing the patches from the link below. Note that you still need to install Python 3.8 and dependencies manually. https:\u002F\u002Fgithub.com\u002FjosStorer\u002Fwails\u002Freleases\u002Ftag\u002Fv2.9.2x\r\n\r\n### Fixes\r\n- fix the issue of failing to load the state for RWKV7\r\n- Fix the abnormal behavior when passing a Tool Definition array. This is a frontend only parameter construction issue.\r\n- fix the issue where the model list did not refresh automatically after downloading the model when using a custom model path\r\n\r\nNote: If you encounter WebView2 crash issues, please try opening the Windows Settings, click on Apps, search for\r\nWebView2, click Modify -> Repair to update your WebView2 runtime.\r\n\r\n## Install\r\n\r\n- Windows: https:\u002F\u002Fgithub.com\u002FjosStorer\u002FRWKV-Runner\u002Fblob\u002Fmaster\u002Fbuild\u002Fwindows\u002FReadme_Install.txt\r\n- MacOS: https:\u002F\u002Fgithub.com\u002FjosStorer\u002FRWKV-Runner\u002Fblob\u002Fmaster\u002Fbuild\u002Fdarwin\u002FReadme_Install.txt\r\n- Linux: https:\u002F\u002Fgithub.com\u002FjosStorer\u002FRWKV-Runner\u002Fblob\u002Fmaster\u002Fbuild\u002Flinux\u002FReadme_Install.txt\r\n- Simple Deploy Example: https:\u002F\u002Fgithub.com\u002FjosStorer\u002FRWKV-Runner\u002Fblob\u002Fmaster\u002FREADME.md#simple-deploy-example\r\n- Server Deploy Examples: https:\u002F\u002Fgithub.com\u002FjosStorer\u002FRWKV-Runner\u002Ftree\u002Fmaster\u002Fdeploy-examples\r\n- Windows 7 Patches: https:\u002F\u002Fgithub.com\u002FjosStorer\u002Fwails\u002Freleases\u002Ftag\u002Fv2.9.2x\r\n","2025-06-27T14:59:57",{"id":222,"version":223,"summary_zh":224,"released_at":225},110051,"v1.9.5","## Changes\n\n- add torch-2.7.1+cu128 precompiled kernels\n![image](https:\u002F\u002Fgithub.com\u002Fuser-attachments\u002Fassets\u002Faa1703ec-da0e-4e3f-820c-9253f4b9bf15)\n- hide unnecessary pop-up consoles on windows\n- The linux binary files released in github releases now depend on libwebkit2gtk-4.1 to support Ubuntu 24.04. This means that versions below Ubuntu 20.04 will no longer be supported for running, and users will have to build it on their own. Additionally, Windows 7 is still supported, but you need to install the KB2999226 patch.\n- add quick think support\n![Image](https:\u002F\u002Fgithub.com\u002Fuser-attachments\u002Fassets\u002Fecf66622-0765-42c9-b8a0-633c30329349)\n- fix the issue where the line breaks in the thinking content did not take effect\n- update manifest.json and defaultModelConfigs\n- bump go-webview2\n\nNote: If you encounter WebView2 crash issues, please try opening the Windows Settings, click on Apps, search for\nWebView2, click Modify -> Repair to update your WebView2 runtime.\n\n## Install\n\n- Windows: https:\u002F\u002Fgithub.com\u002FjosStorer\u002FRWKV-Runner\u002Fblob\u002Fmaster\u002Fbuild\u002Fwindows\u002FReadme_Install.txt\n- MacOS: https:\u002F\u002Fgithub.com\u002FjosStorer\u002FRWKV-Runner\u002Fblob\u002Fmaster\u002Fbuild\u002Fdarwin\u002FReadme_Install.txt\n- Linux: https:\u002F\u002Fgithub.com\u002FjosStorer\u002FRWKV-Runner\u002Fblob\u002Fmaster\u002Fbuild\u002Flinux\u002FReadme_Install.txt\n- Simple Deploy Example: https:\u002F\u002Fgithub.com\u002FjosStorer\u002FRWKV-Runner\u002Fblob\u002Fmaster\u002FREADME.md#simple-deploy-example\n- Server Deploy Examples: https:\u002F\u002Fgithub.com\u002FjosStorer\u002FRWKV-Runner\u002Ftree\u002Fmaster\u002Fdeploy-examples\n","2025-06-25T12:34:47",{"id":227,"version":228,"summary_zh":229,"released_at":230},110052,"v1.9.4","## Changes\n\n- Add NVIDIA hardware info display to Settings Page with PyTorch version switching capability. Auto-select optimal PyTorch version during initial setup based on detected hardware. (Currently only works on Windows)\n![image](https:\u002F\u002Fgithub.com\u002Fuser-attachments\u002Fassets\u002Fcce4b8ce-a920-451d-8f5f-c497b06a6339)\n![image](https:\u002F\u002Fgithub.com\u002Fuser-attachments\u002Fassets\u002Faa1703ec-da0e-4e3f-820c-9253f4b9bf15)\n- temporarily disable the standard WebGPU strategy as it's outdated\n- improve details\n\nNote: If you encounter WebView2 crash issues, please try opening the Windows Settings, click on Apps, search for\nWebView2, click Modify -> Repair to update your WebView2 runtime.\n\n## Install\n\n- Windows: https:\u002F\u002Fgithub.com\u002FjosStorer\u002FRWKV-Runner\u002Fblob\u002Fmaster\u002Fbuild\u002Fwindows\u002FReadme_Install.txt\n- MacOS: https:\u002F\u002Fgithub.com\u002FjosStorer\u002FRWKV-Runner\u002Fblob\u002Fmaster\u002Fbuild\u002Fdarwin\u002FReadme_Install.txt\n- Linux: https:\u002F\u002Fgithub.com\u002FjosStorer\u002FRWKV-Runner\u002Fblob\u002Fmaster\u002Fbuild\u002Flinux\u002FReadme_Install.txt\n- Simple Deploy Example: https:\u002F\u002Fgithub.com\u002FjosStorer\u002FRWKV-Runner\u002Fblob\u002Fmaster\u002FREADME.md#simple-deploy-example\n- Server Deploy Examples: https:\u002F\u002Fgithub.com\u002FjosStorer\u002FRWKV-Runner\u002Ftree\u002Fmaster\u002Fdeploy-examples\n","2025-06-24T17:04:56",{"id":232,"version":233,"summary_zh":234,"released_at":235},110053,"v1.9.3","## Changes\r\n\r\n- bump rwkv pip (improve VRAM usage when using rwkv7)\r\n- the reasoning model renderer no longer modifies the original response's `\u003Cthink>` tags, but only processes them during the rendering process, and fixes the issue where markdown was not correctly rendered when rendering the `\u003Cthink>` tags in certain cases\r\n- update the shortcut API list and model list in the settings, add OpenRouter and DeepSeek, and update the list with the most commonly used models at present\r\n- update rwkv.cpp model conversion script (3e97b6ff0e3dddf1e1aece8eda843a984ec8d79a) @MollySophia \r\n- update manifest (add rwkv7-g1 reasoning model)\r\n- add `make devq` command to improve the startup and reload speed during project development. Requires `go install github.com\u002FjosStorer\u002Fwails\u002Fv2\u002Fcmd\u002Fwails@v2.9.2x`\r\n\r\nNote: If you encounter WebView2 crash issues, please try opening the Windows Settings, click on Apps, search for\r\nWebView2, click Modify -> Repair to update your WebView2 runtime.\r\n\r\n## Install\r\n\r\n- Windows: https:\u002F\u002Fgithub.com\u002FjosStorer\u002FRWKV-Runner\u002Fblob\u002Fmaster\u002Fbuild\u002Fwindows\u002FReadme_Install.txt\r\n- MacOS: https:\u002F\u002Fgithub.com\u002FjosStorer\u002FRWKV-Runner\u002Fblob\u002Fmaster\u002Fbuild\u002Fdarwin\u002FReadme_Install.txt\r\n- Linux: https:\u002F\u002Fgithub.com\u002FjosStorer\u002FRWKV-Runner\u002Fblob\u002Fmaster\u002Fbuild\u002Flinux\u002FReadme_Install.txt\r\n- Simple Deploy Example: https:\u002F\u002Fgithub.com\u002FjosStorer\u002FRWKV-Runner\u002Fblob\u002Fmaster\u002FREADME.md#simple-deploy-example\r\n- Server Deploy Examples: https:\u002F\u002Fgithub.com\u002FjosStorer\u002FRWKV-Runner\u002Ftree\u002Fmaster\u002Fdeploy-examples\r\n","2025-05-19T16:40:51",{"id":237,"version":238,"summary_zh":239,"released_at":240},110054,"v1.9.2","## Changes\n\n- deepseek compatible prefix mode api support\n- add deepthink toggle button\n- chores\n\nThe image below shows the effect of RWKV7-G1 1.5B model trained to 16% completion. The results may not be optimal as it's mainly for demonstrating the API server and UI functionality.\n\n![image](https:\u002F\u002Fgithub.com\u002Fuser-attachments\u002Fassets\u002F0890d491-9379-4b8d-ba2d-fde5fb2ee48e)\n\nNote: If you encounter WebView2 crash issues, please try opening the Windows Settings, click on Apps, search for\nWebView2, click Modify -> Repair to update your WebView2 runtime.\n\n## Install\n\n- Windows: https:\u002F\u002Fgithub.com\u002FjosStorer\u002FRWKV-Runner\u002Fblob\u002Fmaster\u002Fbuild\u002Fwindows\u002FReadme_Install.txt\n- MacOS: https:\u002F\u002Fgithub.com\u002FjosStorer\u002FRWKV-Runner\u002Fblob\u002Fmaster\u002Fbuild\u002Fdarwin\u002FReadme_Install.txt\n- Linux: https:\u002F\u002Fgithub.com\u002FjosStorer\u002FRWKV-Runner\u002Fblob\u002Fmaster\u002Fbuild\u002Flinux\u002FReadme_Install.txt\n- Simple Deploy Example: https:\u002F\u002Fgithub.com\u002FjosStorer\u002FRWKV-Runner\u002Fblob\u002Fmaster\u002FREADME.md#simple-deploy-example\n- Server Deploy Examples: https:\u002F\u002Fgithub.com\u002FjosStorer\u002FRWKV-Runner\u002Ftree\u002Fmaster\u002Fdeploy-examples\n","2025-03-12T15:38:22",{"id":242,"version":243,"summary_zh":244,"released_at":245},110055,"v1.9.1","## Changes\n\n- bump webgpu(python) (rwkv7 support) (https:\u002F\u002Fgithub.com\u002Fcryscan\u002Fweb-rwkv-py)\n- bump rwkv.cpp (rwkv7 support) (https:\u002F\u002Fgithub.com\u002FRWKV\u002Frwkv.cpp)\n- reasoning model renderer support (like deepseek-r1, Qwen qwq)\n- smart scroll area support, no longer locked to bottom when generating\n- precision of penalty can be set to 0.01\n- update manifest and default configs\n- update welcome message\n\n![image](https:\u002F\u002Fgithub.com\u002Fuser-attachments\u002Fassets\u002F9104efe8-ed7a-4cad-b30b-738845db41e5)\n\nNote: If you encounter WebView2 crash issues, please try opening the Windows Settings, click on Apps, search for\nWebView2, click Modify -> Repair to update your WebView2 runtime.\n\n## Install\n\n- Windows: https:\u002F\u002Fgithub.com\u002FjosStorer\u002FRWKV-Runner\u002Fblob\u002Fmaster\u002Fbuild\u002Fwindows\u002FReadme_Install.txt\n- MacOS: https:\u002F\u002Fgithub.com\u002FjosStorer\u002FRWKV-Runner\u002Fblob\u002Fmaster\u002Fbuild\u002Fdarwin\u002FReadme_Install.txt\n- Linux: https:\u002F\u002Fgithub.com\u002FjosStorer\u002FRWKV-Runner\u002Fblob\u002Fmaster\u002Fbuild\u002Flinux\u002FReadme_Install.txt\n- Simple Deploy Example: https:\u002F\u002Fgithub.com\u002FjosStorer\u002FRWKV-Runner\u002Fblob\u002Fmaster\u002FREADME.md#simple-deploy-example\n- Server Deploy Examples: https:\u002F\u002Fgithub.com\u002FjosStorer\u002FRWKV-Runner\u002Ftree\u002Fmaster\u002Fdeploy-examples\n","2025-03-09T14:15:41",{"id":247,"version":248,"summary_zh":249,"released_at":250},110056,"v1.9.0","## Changes\n\n- fix the handling of AVOID_REPEAT_TOKENS (Chinese punctuation) that may lead to rwkv7 fp16 overflow, causing the generation to terminate\n- fix the misidentification of rwkv5 as rwkv7 (#407)\n- improve version comparison\n\nNote: If you encounter WebView2 crash issues, please try opening the Windows Settings, click on Apps, search for\nWebView2, click Modify -> Repair to update your WebView2 runtime.\n\n## Install\n\n- Windows: https:\u002F\u002Fgithub.com\u002FjosStorer\u002FRWKV-Runner\u002Fblob\u002Fmaster\u002Fbuild\u002Fwindows\u002FReadme_Install.txt\n- MacOS: https:\u002F\u002Fgithub.com\u002FjosStorer\u002FRWKV-Runner\u002Fblob\u002Fmaster\u002Fbuild\u002Fdarwin\u002FReadme_Install.txt\n- Linux: https:\u002F\u002Fgithub.com\u002FjosStorer\u002FRWKV-Runner\u002Fblob\u002Fmaster\u002Fbuild\u002Flinux\u002FReadme_Install.txt\n- Simple Deploy Example: https:\u002F\u002Fgithub.com\u002FjosStorer\u002FRWKV-Runner\u002Fblob\u002Fmaster\u002FREADME.md#simple-deploy-example\n- Server Deploy Examples: https:\u002F\u002Fgithub.com\u002FjosStorer\u002FRWKV-Runner\u002Ftree\u002Fmaster\u002Fdeploy-examples\n","2024-12-13T06:13:18",{"id":252,"version":253,"summary_zh":254,"released_at":255},110057,"v1.8.9","## Changes\n\n- rwkv7 support (CPU and CUDA Mode only)\n\nNote: If you encounter WebView2 crash issues, please try opening the Windows Settings, click on Apps, search for\nWebView2, click Modify -> Repair to update your WebView2 runtime.\n\n## Install\n\n- Windows: https:\u002F\u002Fgithub.com\u002FjosStorer\u002FRWKV-Runner\u002Fblob\u002Fmaster\u002Fbuild\u002Fwindows\u002FReadme_Install.txt\n- MacOS: https:\u002F\u002Fgithub.com\u002FjosStorer\u002FRWKV-Runner\u002Fblob\u002Fmaster\u002Fbuild\u002Fdarwin\u002FReadme_Install.txt\n- Linux: https:\u002F\u002Fgithub.com\u002FjosStorer\u002FRWKV-Runner\u002Fblob\u002Fmaster\u002Fbuild\u002Flinux\u002FReadme_Install.txt\n- Simple Deploy Example: https:\u002F\u002Fgithub.com\u002FjosStorer\u002FRWKV-Runner\u002Fblob\u002Fmaster\u002FREADME.md#simple-deploy-example\n- Server Deploy Examples: https:\u002F\u002Fgithub.com\u002FjosStorer\u002FRWKV-Runner\u002Ftree\u002Fmaster\u002Fdeploy-examples\n","2024-12-11T15:41:02",{"id":257,"version":258,"summary_zh":259,"released_at":260},110058,"v1.8.8","## Changes\r\n\r\n- potential crash fix (#396)\r\n\r\nNote: If you encounter WebView2 crash issues, please try opening the Windows Settings, click on Apps, search for WebView2, click Modify -> Repair to update your WebView2 runtime.\r\n\r\n## Install\r\n\r\n- Windows: https:\u002F\u002Fgithub.com\u002FjosStorer\u002FRWKV-Runner\u002Fblob\u002Fmaster\u002Fbuild\u002Fwindows\u002FReadme_Install.txt\r\n- MacOS: https:\u002F\u002Fgithub.com\u002FjosStorer\u002FRWKV-Runner\u002Fblob\u002Fmaster\u002Fbuild\u002Fdarwin\u002FReadme_Install.txt\r\n- Linux: https:\u002F\u002Fgithub.com\u002FjosStorer\u002FRWKV-Runner\u002Fblob\u002Fmaster\u002Fbuild\u002Flinux\u002FReadme_Install.txt\r\n- Simple Deploy Example: https:\u002F\u002Fgithub.com\u002FjosStorer\u002FRWKV-Runner\u002Fblob\u002Fmaster\u002FREADME.md#simple-deploy-example\r\n- Server Deploy Examples: https:\u002F\u002Fgithub.com\u002FjosStorer\u002FRWKV-Runner\u002Ftree\u002Fmaster\u002Fdeploy-examples\r\n","2024-10-20T07:57:36",{"id":262,"version":263,"summary_zh":264,"released_at":265},110059,"v1.8.7","## v1.8.7\n\n- withdrawing the obfuscated tiny package, as it caused some exceptions in the html webui\n\n## v1.8.6\n\n### Features\n\n- feat(python backend): function call support (#368) Great thanks to @EliwiiKeeya\n\n![image](https:\u002F\u002Fgithub.com\u002Fuser-attachments\u002Fassets\u002Fd1686c4a-4b35-4482-b7d6-ad206b93f20e)\n\n- feat(ui): add navigator for web on narrow screen (#376) Great thanks to @HaloWang\n\n\u003Cimg src=\"https:\u002F\u002Fgithub.com\u002Fuser-attachments\u002Fassets\u002F72fa06a4-7b36-4eb5-a5dc-e1ab140adb20\" width=\"256\"\u002F>\n\n- windows installer support: https:\u002F\u002Fgithub.com\u002FjosStorer\u002FRWKV-Runner\u002Freleases\u002Flatest\u002Fdownload\u002FRWKV-Runner-amd64-installer.exe\n- add penalty_decay to the Completion Page\n\n### Improvements\n\n- improve WSL installation condition detection\n\n### Chores\n\n- downgrade to golang1.20 for compatibility with windows7 (#377)\n- update manifest.json (hide old models and add new models)\n- html-webui.zip is now added to the release\n\n## Install\n\n- Windows: https:\u002F\u002Fgithub.com\u002FjosStorer\u002FRWKV-Runner\u002Fblob\u002Fmaster\u002Fbuild\u002Fwindows\u002FReadme_Install.txt\n- MacOS: https:\u002F\u002Fgithub.com\u002FjosStorer\u002FRWKV-Runner\u002Fblob\u002Fmaster\u002Fbuild\u002Fdarwin\u002FReadme_Install.txt\n- Linux: https:\u002F\u002Fgithub.com\u002FjosStorer\u002FRWKV-Runner\u002Fblob\u002Fmaster\u002Fbuild\u002Flinux\u002FReadme_Install.txt\n- Simple Deploy Example: https:\u002F\u002Fgithub.com\u002FjosStorer\u002FRWKV-Runner\u002Fblob\u002Fmaster\u002FREADME.md#simple-deploy-example\n- Server Deploy Examples: https:\u002F\u002Fgithub.com\u002FjosStorer\u002FRWKV-Runner\u002Ftree\u002Fmaster\u002Fdeploy-examples\n","2024-08-29T07:46:58",{"id":267,"version":268,"summary_zh":269,"released_at":270},110060,"v1.8.6","## Changes\n\n### Features\n\n- feat(python backend): function call support (#368) Great thanks to @EliwiiKeeya\n\n![image](https:\u002F\u002Fgithub.com\u002Fuser-attachments\u002Fassets\u002Fd1686c4a-4b35-4482-b7d6-ad206b93f20e)\n\n- feat(ui): add navigator for web on narrow screen (#376) Great thanks to @HaloWang\n\n\u003Cimg src=\"https:\u002F\u002Fgithub.com\u002Fuser-attachments\u002Fassets\u002F72fa06a4-7b36-4eb5-a5dc-e1ab140adb20\" width=\"256\"\u002F>\n\n- windows installer support: https:\u002F\u002Fgithub.com\u002FjosStorer\u002FRWKV-Runner\u002Freleases\u002Flatest\u002Fdownload\u002FRWKV-Runner-amd64-installer.exe\n- add penalty_decay to the Completion Page\n\n### Improvements\n\n- improve WSL installation condition detection\n\n### Chores\n\n- downgrade to golang1.20 for compatibility with windows7 (#377)\n- update manifest.json (hide old models and add new models)\n- html-webui.zip is now added to the release\n\n## Install\n\n- Windows: https:\u002F\u002Fgithub.com\u002FjosStorer\u002FRWKV-Runner\u002Fblob\u002Fmaster\u002Fbuild\u002Fwindows\u002FReadme_Install.txt\n- MacOS: https:\u002F\u002Fgithub.com\u002FjosStorer\u002FRWKV-Runner\u002Fblob\u002Fmaster\u002Fbuild\u002Fdarwin\u002FReadme_Install.txt\n- Linux: https:\u002F\u002Fgithub.com\u002FjosStorer\u002FRWKV-Runner\u002Fblob\u002Fmaster\u002Fbuild\u002Flinux\u002FReadme_Install.txt\n- Simple Deploy Example: https:\u002F\u002Fgithub.com\u002FjosStorer\u002FRWKV-Runner\u002Fblob\u002Fmaster\u002FREADME.md#simple-deploy-example\n- Server Deploy Examples: https:\u002F\u002Fgithub.com\u002FjosStorer\u002FRWKV-Runner\u002Ftree\u002Fmaster\u002Fdeploy-examples\n","2024-08-29T07:15:50",{"id":272,"version":273,"summary_zh":274,"released_at":275},110061,"v1.8.5","## Changes\n\n### Features\n\n- allow the use of the devtools (Ctrl\u002FCmd+Shift+F12)\n- allow custom user avatar image of presets\n\n### Upgrades\n\n- bump webgpu(python) (https:\u002F\u002Fgithub.com\u002Fcryscan\u002Fweb-rwkv-py)\n- bump rwkv.cpp (rwkv6 support) (https:\u002F\u002Fgithub.com\u002FRWKV\u002Frwkv.cpp)\n\n### Improvements\n\n- improve prompts\n- improve error notifications during fine-tuning\n\n### Fixes\n\n- fix: #353, numpy2.0 error when fine-tuning\n\n## Install\n\n- Windows: https:\u002F\u002Fgithub.com\u002FjosStorer\u002FRWKV-Runner\u002Fblob\u002Fmaster\u002Fbuild\u002Fwindows\u002FReadme_Install.txt\n- MacOS: https:\u002F\u002Fgithub.com\u002FjosStorer\u002FRWKV-Runner\u002Fblob\u002Fmaster\u002Fbuild\u002Fdarwin\u002FReadme_Install.txt\n- Linux: https:\u002F\u002Fgithub.com\u002FjosStorer\u002FRWKV-Runner\u002Fblob\u002Fmaster\u002Fbuild\u002Flinux\u002FReadme_Install.txt\n- Simple Deploy Example: https:\u002F\u002Fgithub.com\u002FjosStorer\u002FRWKV-Runner\u002Fblob\u002Fmaster\u002FREADME.md#simple-deploy-example\n- Server Deploy Examples: https:\u002F\u002Fgithub.com\u002FjosStorer\u002FRWKV-Runner\u002Ftree\u002Fmaster\u002Fdeploy-examples\n","2024-07-25T15:57:32",{"id":277,"version":278,"summary_zh":279,"released_at":280},110062,"v1.8.4","## v1.8.4\r\n\r\n- fix f05a4ac, `__init__.py` is not embedded\r\n\r\n## v1.8.3\r\n\r\n### Deprecations\r\n\r\n- rwkv-beta is deprecated\r\n\r\n### Upgrades\r\n\r\n- bump webgpu(python) (https:\u002F\u002Fgithub.com\u002Fcryscan\u002Fweb-rwkv-py)\r\n- sync https:\u002F\u002Fgithub.com\u002FJL-er\u002FRWKV-PEFT (LoRA)\r\n\r\n### Improvements\r\n\r\n- improve default LoRA fine-tune params\r\n\r\n### Fixes\r\n\r\n- fix #342, #345: cannot import name 'packaging' from 'pkg_resources'\r\n- fix the huge error prompt that pops up when running in webgpu mode\r\n\r\n## Install\r\n\r\n- Windows: https:\u002F\u002Fgithub.com\u002FjosStorer\u002FRWKV-Runner\u002Fblob\u002Fmaster\u002Fbuild\u002Fwindows\u002FReadme_Install.txt\r\n- MacOS: https:\u002F\u002Fgithub.com\u002FjosStorer\u002FRWKV-Runner\u002Fblob\u002Fmaster\u002Fbuild\u002Fdarwin\u002FReadme_Install.txt\r\n- Linux: https:\u002F\u002Fgithub.com\u002FjosStorer\u002FRWKV-Runner\u002Fblob\u002Fmaster\u002Fbuild\u002Flinux\u002FReadme_Install.txt\r\n- Simple Deploy Example: https:\u002F\u002Fgithub.com\u002FjosStorer\u002FRWKV-Runner\u002Fblob\u002Fmaster\u002FREADME.md#simple-deploy-example\r\n- Server Deploy Examples: https:\u002F\u002Fgithub.com\u002FjosStorer\u002FRWKV-Runner\u002Ftree\u002Fmaster\u002Fdeploy-examples\r\n","2024-05-29T08:42:51",{"id":282,"version":283,"summary_zh":284,"released_at":285},110063,"v1.8.3","## Deprecations\n\n- rwkv-beta is deprecated\n\n## Upgrades\n\n- bump webgpu(python) (https:\u002F\u002Fgithub.com\u002Fcryscan\u002Fweb-rwkv-py)\n- sync https:\u002F\u002Fgithub.com\u002FJL-er\u002FRWKV-PEFT (LoRA)\n\n## Improvements\n\n- improve default LoRA fine-tune params\n\n## Fixes\n\n- fix #342, #345: cannot import name 'packaging' from 'pkg_resources'\n- fix the huge error prompt that pops up when running in webgpu mode\n\n## Install\n\n- Windows: https:\u002F\u002Fgithub.com\u002FjosStorer\u002FRWKV-Runner\u002Fblob\u002Fmaster\u002Fbuild\u002Fwindows\u002FReadme_Install.txt\n- MacOS: https:\u002F\u002Fgithub.com\u002FjosStorer\u002FRWKV-Runner\u002Fblob\u002Fmaster\u002Fbuild\u002Fdarwin\u002FReadme_Install.txt\n- Linux: https:\u002F\u002Fgithub.com\u002FjosStorer\u002FRWKV-Runner\u002Fblob\u002Fmaster\u002Fbuild\u002Flinux\u002FReadme_Install.txt\n- Simple Deploy Example: https:\u002F\u002Fgithub.com\u002FjosStorer\u002FRWKV-Runner\u002Fblob\u002Fmaster\u002FREADME.md#simple-deploy-example\n- Server Deploy Examples: https:\u002F\u002Fgithub.com\u002FjosStorer\u002FRWKV-Runner\u002Ftree\u002Fmaster\u002Fdeploy-examples\n","2024-05-28T15:15:03",{"id":287,"version":288,"summary_zh":289,"released_at":290},110064,"v1.8.2","## Changes\n\n- improve dynamic state api\n- fix a tps error\n\n## Install\n\n- Windows: https:\u002F\u002Fgithub.com\u002FjosStorer\u002FRWKV-Runner\u002Fblob\u002Fmaster\u002Fbuild\u002Fwindows\u002FReadme_Install.txt\n- MacOS: https:\u002F\u002Fgithub.com\u002FjosStorer\u002FRWKV-Runner\u002Fblob\u002Fmaster\u002Fbuild\u002Fdarwin\u002FReadme_Install.txt\n- Linux: https:\u002F\u002Fgithub.com\u002FjosStorer\u002FRWKV-Runner\u002Fblob\u002Fmaster\u002Fbuild\u002Flinux\u002FReadme_Install.txt\n- Simple Deploy Example: https:\u002F\u002Fgithub.com\u002FjosStorer\u002FRWKV-Runner\u002Fblob\u002Fmaster\u002FREADME.md#simple-deploy-example\n- Server Deploy Examples: https:\u002F\u002Fgithub.com\u002FjosStorer\u002FRWKV-Runner\u002Ftree\u002Fmaster\u002Fdeploy-examples\n","2024-05-16T06:00:12",{"id":292,"version":293,"summary_zh":294,"released_at":295},110065,"v1.8.1","## Changes\n\n### Features\n\n- add support for dynamic state-tuned models\n\n![image](https:\u002F\u002Fgithub.com\u002FjosStorer\u002FRWKV-Runner\u002Fassets\u002F13366013\u002F42206150-1321-4791-89a2-8d5c4f655ed8)\n\n### Upgrades\n\n- bump webgpu mode [ai00_server v0.4.8](https:\u002F\u002Fgithub.com\u002FAi00-X\u002Fai00_server)\n\n### Improvements\n\n- add tps console output\n- add torch cnMirror\n- disable pre_ffn and head_qk\n- improve frontend details\n\n### Chores\n\n- update manifest.json and defaultModelConfigs\n\n## Install\n\n- Windows: https:\u002F\u002Fgithub.com\u002FjosStorer\u002FRWKV-Runner\u002Fblob\u002Fmaster\u002Fbuild\u002Fwindows\u002FReadme_Install.txt\n- MacOS: https:\u002F\u002Fgithub.com\u002FjosStorer\u002FRWKV-Runner\u002Fblob\u002Fmaster\u002Fbuild\u002Fdarwin\u002FReadme_Install.txt\n- Linux: https:\u002F\u002Fgithub.com\u002FjosStorer\u002FRWKV-Runner\u002Fblob\u002Fmaster\u002Fbuild\u002Flinux\u002FReadme_Install.txt\n- Simple Deploy Example: https:\u002F\u002Fgithub.com\u002FjosStorer\u002FRWKV-Runner\u002Fblob\u002Fmaster\u002FREADME.md#simple-deploy-example\n- Server Deploy Examples: https:\u002F\u002Fgithub.com\u002FjosStorer\u002FRWKV-Runner\u002Ftree\u002Fmaster\u002Fdeploy-examples\n","2024-05-12T15:45:33"]