GraphCanon
Home/Model Training/verl
verl logo

verl

verl-project/verl

A Flexible and Efficient RL Post-Training Framework

GitHub Website

GraphCanon updated today · GitHub synced today

22k
Stars
4.2k
Forks
1.6k
Open issues
89
Watchers
1d
Last push
Python Apache-2.0Created Oct 31, 2024

Trust & integrity

Full report
Maintenance
Very active (0d since push)
As of today · Source: github_public_v1
Provenance
Not a fork · Organization account
As of today · Source: github_public_v1
Security (OSV)
2 low (2 low)
As of today · Source: osv@v1

Public GitHub metadata and optional OSV dependency scans. Signals, not a guarantee. Trust methodology.

Overview

verl/HybridFlow is a Python framework designed for flexible and efficient reinforcement learning (RL) post-training, offering algorithms like PPO and GRPO with detailed documentation and reproducible baselines for coding and math tasks. It includes components like Ray trainer, model engine, and support for advanced usage such as adding models using FSDP or Megatron-LM backends.

Capability facts

Languages
python

Source: github.language+pyproject.toml · Jul 11, 2026

Categories

Model Training

Compatibility

Sourced claims from the README excerpt - not unsourced marketing copy.

Python runtimePython

Source: README excerpt (regex_v1, Jul 11, 2026)

icit **`VERL_COMMIT`** (and related submodule / recipe-folder SHAs) so you can `pip install verl@git+…@<sha>` without guessing. See [`recipe/README.md`](recipe/README.md)
Source link

Tags

reinforcement-learningppopythonrlpost-traininggrpo

README

Getting Started

Documentation

Quickstart:

Running a PPO example step-by-step:

Reproducible algorithm baselines:

Algorithm recipes (recipe/):

  • Optional workflows and baselines live under recipe/. Each recipe subdirectory includes a small REQUIRED_VERL.txt file describing the intended verl install: pinned recipes use a tag or fixed git SHA; rolling recipes record an explicit VERL_COMMIT (and related submodule / recipe-folder SHAs) so you can pip install verl@git+…@<sha> without guessing. See recipe/README.md for the full index and links.

For code explanation and advance usage (extension):

Blogs from the community