# hiyouga/EasyR1

EasyR1: An Efficient, Scalable, Multi-Modality RL Training Framework based on veRL

Repository: https://github.com/hiyouga/EasyR1
Canonical: https://ross.abutalabs.com/products/easyr1
Homepage: https://verl.readthedocs.io
Language: Python
License: Apache-2.0
License Family: permissive
Topics: ai, gpt, llm, nlp, reinforcement-learning, rl, deepseek, qwen
Last push: 2026-08-26T21:14:17+00:00

## Health v2 (maintenance only)
Score: 65/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 99, release rhythm 36, longevity 39
- inputs: {"age_days": 557, "days_push": 7, "days_rel": 349, "gap_med": 77.5, "n_releases_24m": 3}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 5129, forks 387 (observed 2026-08-28T04:09:10.997636+00:00)

## What it is
EasyR1 is an efficient, scalable reinforcement learning training framework for large language models and vision-language models, built as a fork of veRL. It supports algorithms like GRPO, DAPO, and GSPO, leveraging HybridEngine and vLLM's SPMD mode for performance.

## Use cases
- train an LLM with GRPO reinforcement learning
- fine-tune Qwen vision-language models with RL
- run RLHF post-training on DeepSeek-R1 distill models
- scale multi-modal RL training across GPUs
- apply LoRA-based reinforcement learning to a 7B model
- train language models with DAPO or GSPO algorithms

## When to choose
- you need RL post-training (GRPO/DAPO/GSPO) for LLMs or VLMs
- you want a veRL-based framework with vision-language model support
- you need scalable multi-GPU RL training with vLLM rollouts
- you want checkpointing, experiment tracking, and LoRA in one RL framework

## When to avoid
- you only need supervised fine-tuning without RL
- you lack multi-GPU hardware or Docker support
- you need a simple inference or serving solution rather than training
- you prefer a framework with broader model coverage than the supported Qwen/Llama/DeepSeek families

## Facets
- artifact type: framework
- maturity: active
- function: llm-training, reinforcement-learning, machine-learning, gpu-computing
- domain: large-language-models, reinforcement-learning, machine-learning, deep-learning
- platform: python
- tags: grpo, dapo, verl, vllm, vision-language-models, rlhf, qwen, deepseek, lora, multi-modal, gpu, docker, linux

## Member repositories
- hiyouga/EasyR1 (main) score 65

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:09:10.997636+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 2026-08-29T18:02:03.004517+00:00, confidence not recorded.
  - readme: https://github.com/hiyouga/EasyR1 (fetched 2026-08-28T04:09:10.997636+00:00, sha 4368af2dab48)
- Data as of 2026-08-30T08:39:29.467469+00:00.