# NVIDIA-NeMo/RL

Scalable toolkit for efficient model reinforcement

Repository: https://github.com/NVIDIA-NeMo/RL
Canonical: https://ross.abutalabs.com/products/nvidia-nemo-rl
Homepage: https://docs.nvidia.com/nemo/rl/latest/index.html
Language: Python
License: Apache-2.0
License Family: permissive
Last push: 2026-08-26T20:49:10+00:00

## Health v2 (maintenance only)
Score: 81/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 99, release rhythm 83, longevity 38
- inputs: {"age_days": 535, "days_push": 7, "days_rel": 35, "gap_med": 60, "n_releases_24m": 10}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1961, forks 534 (observed 2026-08-28T04:05:59.496814+00:00)

## What it is
NeMo RL is NVIDIA's open-source post-training library for scaling reinforcement learning methods (GRPO, PPO, DPO, SFT, distillation) on LLMs and vision-language models. It supports PyTorch DTensor and Megatron Core training backends with vLLM/SGLang generation, Ray-based orchestration, and multi-node Slurm or Kubernetes deployment.

## Use cases
- train an LLM with GRPO on math reasoning tasks
- run RLHF post-training on a Qwen or Llama model across multiple GPUs
- fine-tune a vision-language model with SFT or GRPO
- perform on-policy distillation from a teacher model
- scale RL training on a multi-node Slurm or Kubernetes cluster
- reproduce NVIDIA Nemotron model post-training recipes
- run multi-turn RL with tool use environments

## When to choose
- you need scalable, multi-node RL post-training for large LLMs or VLMs
- you want Megatron Core parallelism (TP/PP/CP/EP) for very large models
- you want Hugging Face model support with fast vLLM rollouts
- you need reproducible recipes for GRPO, PPO, DPO, or distillation

## When to avoid
- you only need simple single-GPU supervised fine-tuning without RL
- you have no NVIDIA GPUs or CUDA environment
- you need a lightweight library without Docker or cluster infrastructure
- you are training small non-transformer models with standard RL algorithms

## Facets
- artifact type: library
- maturity: active
- function: machine-learning, llm-training, reinforcement-learning, gpu-computing, benchmarking
- domain: large-language-models, machine-learning, deep-learning, gpu-computing, developer-tools
- platform: python, cloud
- tags: post-training, grpo, ppo, dpo, sft, rlhf, vllm, megatron, ray, vlm, distillation, multi-node-training, linux, gpu, docker, kubernetes

## Member repositories
- NVIDIA-NeMo/RL (main) score 81

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:05:59.496814+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T03:05:36.835110+00:00, confidence not recorded.
  - readme: https://github.com/NVIDIA-NeMo/RL (fetched 2026-08-28T04:05:59.496814+00:00, sha 27a2a7ebb0df)
  - homepage: https://docs.nvidia.com/nemo/rl/latest/index.html (fetched 2026-08-29T10:45:41.448975+00:00, sha cbeb1f069028)
  - site_page: https://docs.nvidia.com/nemo/rl/latest/about/overview.html (fetched 2026-08-29T10:45:41.459075+00:00, sha 1daaa53fdc96)
  - site_page: https://docs.nvidia.com/nemo/rl/latest/about/performance-summary.html (fetched 2026-08-29T10:45:41.460799+00:00, sha adb15df58fc2)
  - site_page: https://docs.nvidia.com/nemo/rl/latest/about/model-support.html (fetched 2026-08-29T10:45:41.462435+00:00, sha 505900f19323)
  - site_page: https://docs.nvidia.com/nemo/rl/latest/about/features.html (fetched 2026-08-29T10:45:41.463948+00:00, sha 8e249dedc9b3)
  - site_page: https://docs.nvidia.com/nemo/rl/latest/about/backends.html (fetched 2026-08-29T10:45:41.465581+00:00, sha c41396a348ce)
  - site_page: https://docs.nvidia.com/nemo/rl/latest/about/quick-start.html (fetched 2026-08-29T10:45:41.467053+00:00, sha ee88bc45fde5)
  - site_page: https://docs.nvidia.com/nemo/rl/latest/about/installation.html (fetched 2026-08-29T10:45:41.468527+00:00, sha 72dc579df597)
  - site_page: https://docs.nvidia.com/nemo/rl/latest/about/algorithms/index.html (fetched 2026-08-29T10:45:41.470539+00:00, sha 8b9958004b35)
- Data as of 2026-08-30T08:39:29.467469+00:00.