Skill · em Dados, IA e pesquisa

torchforge-rl-training

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.

Procedência

Antes de instalar

3 arquivos · 25,5 KB · só texto, nenhum script

Instalar na sua CLI

O comando baixa a versão fixada (commit 57f899e) direto da origem, para a pasta que a CLI lê. Precisa de curl (macOS e Linux); no Windows não há comando, porque o Rook Labs é para macOS.

Claude Code

Neste projeto: instala em .claude/skills/torchforge-rl-training/.

d=".claude/skills/torchforge-rl-training"
u="https://raw.githubusercontent.com/davila7/claude-code-templates/57f899e5394bb8ca166f38eacae8f0853cbfe033/cli-tool/components/skills/ai-research/post-training-torchforge"
curl -fsSL --create-dirs \
  -o "$d/SKILL.md" "$u/SKILL.md" \
  -o "$d/references/api-reference.md" "$u/references/api-reference.md" \
  -o "$d/references/troubleshooting.md" "$u/references/troubleshooting.md"

Global: instala em ~/.claude/skills/torchforge-rl-training/.

d="$HOME/.claude/skills/torchforge-rl-training"
u="https://raw.githubusercontent.com/davila7/claude-code-templates/57f899e5394bb8ca166f38eacae8f0853cbfe033/cli-tool/components/skills/ai-research/post-training-torchforge"
curl -fsSL --create-dirs \
  -o "$d/SKILL.md" "$u/SKILL.md" \
  -o "$d/references/api-reference.md" "$u/references/api-reference.md" \
  -o "$d/references/troubleshooting.md" "$u/references/troubleshooting.md"

Codex

Neste projeto: instala em .agents/skills/torchforge-rl-training/.

d=".agents/skills/torchforge-rl-training"
u="https://raw.githubusercontent.com/davila7/claude-code-templates/57f899e5394bb8ca166f38eacae8f0853cbfe033/cli-tool/components/skills/ai-research/post-training-torchforge"
curl -fsSL --create-dirs \
  -o "$d/SKILL.md" "$u/SKILL.md" \
  -o "$d/references/api-reference.md" "$u/references/api-reference.md" \
  -o "$d/references/troubleshooting.md" "$u/references/troubleshooting.md"

Global: instala em ~/.agents/skills/torchforge-rl-training/.

d="$HOME/.agents/skills/torchforge-rl-training"
u="https://raw.githubusercontent.com/davila7/claude-code-templates/57f899e5394bb8ca166f38eacae8f0853cbfe033/cli-tool/components/skills/ai-research/post-training-torchforge"
curl -fsSL --create-dirs \
  -o "$d/SKILL.md" "$u/SKILL.md" \
  -o "$d/references/api-reference.md" "$u/references/api-reference.md" \
  -o "$d/references/troubleshooting.md" "$u/references/troubleshooting.md"

Antigravity

Neste projeto: instala em .agents/skills/torchforge-rl-training/.

d=".agents/skills/torchforge-rl-training"
u="https://raw.githubusercontent.com/davila7/claude-code-templates/57f899e5394bb8ca166f38eacae8f0853cbfe033/cli-tool/components/skills/ai-research/post-training-torchforge"
curl -fsSL --create-dirs \
  -o "$d/SKILL.md" "$u/SKILL.md" \
  -o "$d/references/api-reference.md" "$u/references/api-reference.md" \
  -o "$d/references/troubleshooting.md" "$u/references/troubleshooting.md"

Global: instala em ~/.gemini/antigravity-cli/skills/torchforge-rl-training/.

d="$HOME/.gemini/antigravity-cli/skills/torchforge-rl-training"
u="https://raw.githubusercontent.com/davila7/claude-code-templates/57f899e5394bb8ca166f38eacae8f0853cbfe033/cli-tool/components/skills/ai-research/post-training-torchforge"
curl -fsSL --create-dirs \
  -o "$d/SKILL.md" "$u/SKILL.md" \
  -o "$d/references/api-reference.md" "$u/references/api-reference.md" \
  -o "$d/references/troubleshooting.md" "$u/references/troubleshooting.md"

Peça ao Rook

Já usa o Rook Labs? Cole no chat do Rook: instale a skill https://rooklabs.sh/marketplace/cct.torchforge-rl-training

Prévia do SKILL.md

---
name: torchforge-rl-training
description: 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.
version: 1.0.0
author: Orchestra Research
license: MIT
tags: [Reinforcement Learning, PyTorch, GRPO, SFT, Monarch, TorchTitan, Meta]
dependencies: [torch>=2.9.0, torchtitan>=0.2.0, vllm, monarch]
---

# 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-ready stability → use **miles** or **verl**
- You want Megatron-native training → use **slime**
- torchforge is experimental and APIs may change

## Key Features

- **Algorithm isolation**: Implement RL algorithms without touching infrastructure
- **Scalability**: From single GPU to thousands via Monarch
- **Modern stack**: TorchTitan (training), vLLM (inference), TorchStore (sync)
- **Loss functions**: GRPO, DAPO, CISPO, GSPO, SAPO built-in

## Architecture Overview

```
┌─────────────────────────────────────────────────────────┐
│ Application Layer (Your Code)                           │
…

Ver todo o marketplace