Skip to content
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
484 changes: 484 additions & 0 deletions docs_roll/i18n/en/code.json

Large diffs are not rendered by default.

14 changes: 14 additions & 0 deletions docs_roll/i18n/en/docusaurus-plugin-content-blog/options.json
Original file line number Diff line number Diff line change
@@ -0,0 +1,14 @@
{
"title": {
"message": "Blog",
"description": "The title for the blog used in SEO"
},
"description": {
"message": "Blog",
"description": "The description for the blog used in SEO"
},
"sidebar.title": {
"message": "Recent posts",
"description": "The label for the left sidebar"
}
}
42 changes: 42 additions & 0 deletions docs_roll/i18n/en/docusaurus-plugin-content-docs/current.json
Original file line number Diff line number Diff line change
@@ -0,0 +1,42 @@
{
"version.label": {
"message": "Next",
"description": "The label for version current"
},
"sidebar.tutorialSidebar.category.DesignImplementation": {
"message": "DesignImplementation",
"description": "The label for category 'DesignImplementation' in sidebar 'tutorialSidebar'"
},
"sidebar.tutorialSidebar.category.DevelopmentGuide": {
"message": "DevelopmentGuide",
"description": "The label for category 'DevelopmentGuide' in sidebar 'tutorialSidebar'"
},
"sidebar.tutorialSidebar.category.QuickStart": {
"message": "QuickStart",
"description": "The label for category 'QuickStart' in sidebar 'tutorialSidebar'"
},
"sidebar.tutorialSidebar.category.UserGuide": {
"message": "UserGuide",
"description": "The label for category 'UserGuide' in sidebar 'tutorialSidebar'"
},
"sidebar.tutorialSidebar.category.agentic": {
"message": "agentic",
"description": "The label for category 'agentic' in sidebar 'tutorialSidebar'"
},
"sidebar.tutorialSidebar.category.algorithms": {
"message": "algorithms",
"description": "The label for category 'algorithms' in sidebar 'tutorialSidebar'"
},
"sidebar.tutorialSidebar.category.ascend": {
"message": "ascend",
"description": "The label for category 'ascend' in sidebar 'tutorialSidebar'"
},
"sidebar.tutorialSidebar.category.backend": {
"message": "backend",
"description": "The label for category 'backend' in sidebar 'tutorialSidebar'"
},
"sidebar.tutorialSidebar.category.pipeline": {
"message": "pipeline",
"description": "The label for category 'pipeline' in sidebar 'tutorialSidebar'"
}
}
34 changes: 34 additions & 0 deletions docs_roll/i18n/en/docusaurus-theme-classic/footer.json
Original file line number Diff line number Diff line change
@@ -0,0 +1,34 @@
{
"link.title.Examples": {
"message": "Examples",
"description": "The title of the footer links column with title=Examples in the footer"
},
"link.title.Community": {
"message": "Community",
"description": "The title of the footer links column with title=Community in the footer"
},
"link.title.More": {
"message": "More",
"description": "The title of the footer links column with title=More in the footer"
},
"link.item.label.ROLL单机实践手册": {
"message": "Single Node Quick Start",
"description": "The label of footer link with label=ROLL单机实践手册 linking to /docs/QuickStart/single_node_quick_start"
},
"link.item.label.配置指南": {
"message": "Config Guide",
"description": "The label of footer link with label=配置指南 linking to /docs/QuickStart/config_guide"
},
"link.item.label.Stack Overflow": {
"message": "Stack Overflow",
"description": "The label of footer link with label=Stack Overflow linking to https://stackoverflow.com/questions/tagged/docusaurus"
},
"link.item.label.GitHub": {
"message": "GitHub",
"description": "The label of footer link with label=GitHub linking to https://github.com/alibaba/ROLL"
},
"copyright": {
"message": "Copyright © 2025 Alibaba.",
"description": "The footer copyright"
}
}
30 changes: 30 additions & 0 deletions docs_roll/i18n/en/docusaurus-theme-classic/navbar.json
Original file line number Diff line number Diff line change
@@ -0,0 +1,30 @@
{
"title": {
"message": "ROLL",
"description": "The title in the navbar"
},
"logo.alt": {
"message": "ROLL Logo",
"description": "The alt text of navbar logo"
},
"item.label.Home": {
"message": "Home",
"description": "Navbar item with label Home"
},
"item.label.Core Algorithms": {
"message": "Core Algorithms",
"description": "Navbar item with label Core Algorithms"
},
"item.label.Research Community": {
"message": "Research Community",
"description": "Navbar item with label Research Community"
},
"item.label.API Docs": {
"message": "API Docs",
"description": "Navbar item with label API Docs"
},
"item.label.GitHub": {
"message": "GitHub",
"description": "Navbar item with label GitHub"
}
}
122 changes: 121 additions & 1 deletion docs_roll/i18n/zh-Hans/code.json
Original file line number Diff line number Diff line change
Expand Up @@ -360,5 +360,125 @@
"theme.tags.tagsPageTitle": {
"message": "标签",
"description": "The title of the tag list page"
},
"like a Reinforcement Learning Algorithm Developer": {
"message": "像一名强化学习算法开发者一样"
},
"Home": {
"message": "首页"
},
"Core Algorithms": {
"message": "核心算法"
},
"Research Community": {
"message": "开源社区"
},
"API Docs": {
"message": "文档"
},
"Open Source Framework · Powerful & Easy": {
"message": "开源框架 · 强大且易用"
},
"An open-source reinforcement learning library by Alibaba, optimized for large-scale language models. Supporting distributed training, multi-task learning, and agent interaction for simpler and more efficient AI model training.": {
"message": "阿里巴巴开源的强化学习库,专为大语言模型优化。支持分布式训练、多任务学习与智能体交互,让 AI 模型训练更简单、更高效。"
},
"Framework Overview": {
"message": "框架概览"
},
"ROLL (Reinforcement Learning Optimization for Large-scale Learning) is an open-source reinforcement learning framework by Alibaba, designed for large-scale language models. Built on Ray distributed architecture, supporting mainstream algorithms like PPO and GRPO, providing complete solutions from research to production.": {
"message": "ROLL(面向大规模学习的强化学习优化框架,Reinforcement Learning Optimization for Large-scale Learning)是阿里巴巴开源的强化学习框架,专为大语言模型设计。基于 Ray 分布式架构构建,支持 PPO、GRPO 等主流算法,提供从研究到生产的完整解决方案。"
},
"Why": {
"message": "为什么"
},
"Choose ROLL": {
"message": "选择 ROLL"
},
"Distributed Architecture": {
"message": "分布式框架"
},
"Ray-based distributed architecture supporting mainstream engines like vLLM, SGLang, Megatron-Core, seamlessly scaling from single machine to large GPU clusters": {
"message": "基于 Ray 的分布式架构,支持 vLLM、SGLang、Megatron-Core 等主流推理引擎,可无缝扩展,从单机环境平滑伸缩至大规模 GPU 集群。"
},
"Multi-task Learning": {
"message": "多任务学习"
},
"Support for multi-task joint training including math reasoning, code generation, and dialogue, with dynamic sampling rate and data weight adjustment": {
"message": "支持数学推理、代码生成和对话等多任务联合训练,具备动态采样率与数据权重调整能力。"
},
"Extremely Easy to Use": {
"message": "开箱即用"
},
"Gym-style clean API design with modular architecture for flexible extension, one-click switching between different backend engines and algorithm configurations": {
"message": "采用 Gym 风格的简洁 API 设计,结合模块化架构以支持灵活扩展,可一键切换不同后端引擎与算法配置。"
},
"Core Advantages": {
"message": "核心优势"
},
"ROLL framework provides comprehensive reinforcement learning support, from model training to agent deployment, every aspect is carefully optimized to make AI training more efficient": {
"message": "ROLL 框架提供全面的强化学习支持,涵盖从模型训练到智能体部署的全流程,每个环节均经过精心优化,让 AI 训练更高效。"
},
"Born for Scale": {
"message": "为规模化而生"
},
"Built on a Ray-based distributed architecture, it supports large-scale cluster training at the thousand-GPU level. Its innovative Rollout scheduler and AutoDeviceMapping module dramatically improve GPU resource utilization .": {
"message": "基于 Ray 的分布式架构构建,支持千卡 GPU 级别的大规模集群训练。其创新的 Rollout 调度器与 AutoDeviceMapping 模块显著提升了 GPU 资源利用率。"
},
"Extreme Training Efficiency": {
"message": "极致训练效率"
},
"Integrates cutting-edge technologies like Megatron-Core, SGLang, and vLLM to significantly accelerate the model training and inference sampling processes .": {
"message": "集成 Megatron-Core、SGLang 和 vLLM 等前沿技术,显著加速模型训练与推理采样过程。"
},
"Rich Algorithms & Scenarios": {
"message": "丰富的算法与场景支持"
},
"Comes with built-in mainstream RL algorithms like PPO and GRPO, and supports multi-task RL and agent interaction scenarios. Its effectiveness has been validated in numerous real-world business applications .": {
"message": "内置 PPO、GRPO 等主流强化学习算法,支持多任务强化学习与智能体交互场景,并已在众多实际业务应用中验证其有效性。"
},
"Open Source and Accessible": {
"message": "开源易用"
},
"ROLL is open-sourced on GitHub (https://github.com/alibaba/ROLL) under the Apache License 2.0, backed by an active community and comprehensive documentation .": {
"message": "ROLL 已在 GitHub(https://github.com/alibaba/ROLL)上开源,采用 Apache License 2.0 许可证,并由活跃的社区和完善的文档提供支持。"
},
"Open Source Community": {
"message": "开源社区"
},
"Join our vibrant open source community, explore cutting-edge reinforcement learning technologies with global AI researchers, and jointly promote the future of LLM and RL": {
"message": "加入我们充满活力的开源社区,与全球 AI 研究者共同探索前沿强化学习技术,携手推动大语言模型与强化学习的未来发展。"
},
"How to Contribute": {
"message": "如何贡献"
},
"Contribute algorithm implementations and performance optimizations": {
"message": "贡献算法实现与性能优化"
},
"Share experimental results and best practices": {
"message": "分享实验结果与最佳实践"
},
"Improve tutorials and learning resources": {
"message": "完善教程与学习资源"
},
"Join Discussion": {
"message": "参与讨论"
},
"WeChat": {
"message": "微信群"
},
"Follow GitHub Repository": {
"message": "关注 GitHub 仓库"
},
"Get Started >": {
"message": "快速入门 >"
},
"Github Stars": {
"message": "Github星标"
},
"Contributors": {
"message": "贡献者"
},
"Commits": {
"message": "提交"
}
}
}
Loading