Skip to main content

Ctrl+K

NeMo-RL

GitHub

NeMo-RL

GitHub

Table of Contents

About

Overview
Performance
Features and Roadmap
Training and Generation Backends
Quick Start
Installation and Prerequisites
Algorithms
Evaluation
Installation: Set Up Clusters
Tips and Tricks

Environment Start

Run on Your Local Workstation
Set Up Clusters

E2E Examples

SFT on OpenMathInstruct-2

Guides

Add New Models
Supervised Fine-Tuning in NeMo RL
Direct Preference Optimization in NeMo RL
An in-depth Walkthrough of DAPO in NeMo RL
An In-depth Walkthrough of GRPO in NeMo RL
GRPO on DeepScaler
Solve a Sliding Puzzle Using GRPO
Reward Model Training in NeMo RL
Environments for GRPO Training
Evaluation
DeepSeek-V3
Model Quirks
Train with Async GRPO

Containers

Build Docker Images

Development

Test NeMo RL
Documentation Development
Debug NeMo RL Applications
Profile GPU with Nsys
FP8 Quantization in NeMo RL
Experiment with Custom vLLM

Design Docs

Design and Philosophy
Padding in NeMo RL
Logger
uv in NeMo RL
Dependency Management
Data Format
Generation Interface
Exporting Checkpoints to Hugging Face Format
Loss functions in NeMo RL
FSDP2 Parallel Plan
Training Backends
Sequence Packing and Dynamic Batching
Environment Variable Precedence in NeMo RL

API Reference

API Reference
- nemo_rl

API Reference
nemo_rl
nemo_rl.models
nemo_rl.models.megatron

`nemo_rl.models.megatron`#

Submodules#

nemo_rl.models.megatron.common
nemo_rl.models.megatron.community_import

previous

nemo_rl.models.huggingface.common

next

nemo_rl.models.megatron.common

On this page

Submodules

Privacy Policy | Your Privacy Choices | Terms of Service | Accessibility | Corporate Policies | Product Security | Contact

Copyright © 2025, NVIDIA Corporation.