torchforge-rl-training

仓库创建 2025年11月3日最近提交 1 个月前SkillHot 收录 22 天前

▸ 精选理由

适合做算法迭代和接入分布式训练工具链的开发者。

▸ 风险提示

可能依赖Meta内部组件或特定版本，需注意兼容性与依赖。

这个 Skill 做什么

Meta的PyTorch原生RL库，分离基础设施与算法以便于快速实验与扩展。

基于 PyTorch 的 RL 库，把基础设施和算法分离，让你只专注算法研发而不用操心分布式训练、推理和权重同步。适合做快速算法实验、对接大规模训练（如 Monarch、TorchTitan）或想要可复用训练组件的团队。特点是清晰的抽象与易扩展的训练管线，降低分布式 RL 的工程复杂度。

▸ 展开 SKILL.md 英文原文

Provides guidance for PyTorch-native agentic RL using torchforge, Meta's library separating infra from algorithms. Use when you want clean RL abstractions, easy algorithm experimentation, or scalable training with Monarch and TorchTitan.

开发编程PyTorchRL库可扩展通用

1.1w

Stars

821

Forks

仓库内 Skill

+761

7 日增星

安装 / 使用

给你的 Agent 一句话（通用）

帮我安装这个 skill：https://raw.githubusercontent.com/Orchestra-Research/AI-Research-SKILLs/main/06-post-training/torchforge/SKILL.md

或 curl 直取 SKILL.md

curl -fsSL "https://raw.githubusercontent.com/Orchestra-Research/AI-Research-SKILLs/main/06-post-training/torchforge/SKILL.md"

SKILL.MD 节选查看完整文件 ↗

# torchforge: PyTorch-Native Agentic RL Library

torchforge is Meta's PyTorch-native RL library that separates infrastructure concerns from algorithm concerns. It enables rapid RL research by letting you focus on algorithms while handling distributed training, inference, and weight sync automatically.

## When to Use torchforge

**Choose torchforge when you need:**
- Clean separation between RL algorithms and infrastructure
- PyTorch-native abstractions (no Ray dependency)
- Easy algorithm experimentation (GRPO, DAPO, SAPO in ~100 lines)
- Scalable training with Monarch actor system
- Integration with TorchTitan for model parallelism

**Consider alternatives when:**
- You need production-rea

via SKILL·HOT · 数据来自 GitHub 公开信息 · 原文版权归作者所有