torchforge-rl-training
Category: ml-training · License: MIT · Version: 1.0.0
Tags: Reinforcement Learning, PyTorch, GRPO, SFT, Monarch, TorchTitan, Meta
When to use it
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.Example requests
Ask your agent in plain language, for example:- “How do I write a custom RL loss in torchforge?”
- “I’m trying to run GRPO on Qwen3-1.7B with GSM8K using torchforge on a box with only 2 A100s and I get ‘Insufficient GPU resources’. Config is in apps/grpo/gsm8k.yaml. What do I change?”
- “I want to experiment with a new policy-gradient variant for math reasoning, with group-relative advantages. I want the algorithm code kept separate from the distributed and inference plumbing, PyTorch-native with no Ray. What stack should I use and how do I get started?”
Install
/plugin marketplace add KalarisLabs/research-agent-skills and install the whole ml-training category with /plugin install ml-training@research-agent-skills.
Related
distributed-llm-pretraining-torchtitanpytorch-lightning-distributed- Skills for machine learning research