An Asynchronous Reinforcement Learning Engine for Omni-Modal Post-Training at Scale
☆578Aug 20, 2026Updated this week
Alternatives and similar repositories for Relax
Users that are interested in Relax are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- An asynchronous streaming data management module for efficient post-training.☆135Updated this week
- Official code, data, and models for "Hint Tuning: Less Data Makes Better Reasoners"☆22Jul 8, 2026Updated last month
- slime is an LLM post-training framework for RL Scaling.☆8,209Updated this week
- Miles is an enterprise-facing reinforcement learning framework for LLM and VLM post-training, forked from and co-evolving with slime.☆2,216Updated this week
- VeOmni: Scaling Any Modality Model Training with Model-Centric Distributed Recipe Zoo☆2,167Updated this week
- 1-Click AI Models by DigitalOcean Gradient • AdDeploy popular AI models on DigitalOcean Gradient GPU virtual machines with just a single click. Zero configuration with optimized deployments.
- An Efficient and User-Friendly Scaling Library for Reinforcement Learning with Large Language Models☆3,368Updated this week
- An LLM post-training framework with vLLM for RL Scaling☆428Updated this week
- The RL Bridge for LLM-based Agent Applications. Made Simple & Flexible.☆5,686Updated this week
- Checkpoint-engine is a simple middleware to update model weights in LLM inference engines☆1,001Aug 12, 2026Updated last week
- An agentic-first RL framework for research (9k lines).☆945Updated this week
- Uni-Agent is a framework for training long-horizon agents.☆523Updated this week
- Implementation of an efficient LLM architecture: the Pair-In / Pair-Out Model (PIPO)☆42Jun 10, 2026Updated 2 months ago
- Bridge Megatron-Core to Hugging Face/Reinforcement Learning☆230Jun 15, 2026Updated 2 months ago
- Dataflow-Oriented Reinforcement Learning for (Multi-)Agentic LLMs☆102Jul 26, 2026Updated 3 weeks ago
- 1-Click AI Models by DigitalOcean Gradient • AdDeploy popular AI models on DigitalOcean Gradient GPU virtual machines with just a single click. Zero configuration with optimized deployments.
- Training library for Megatron-based models with bidirectional Hugging Face conversion capability☆876Updated this week
- A high-performance RL training-inference weight synchronization framework, designed to enable second-level parameter updates from trainin…☆170Updated this week
- [Archived] For the latest updates and community contribution, please visit: https://github.com/Ascend/TransferQueue or https://gitcode.co…☆15Aug 14, 2026Updated last week
- verl/HybridFlow: A Flexible and Efficient RL Post-Training Framework☆23,087Updated this week
- Allow torch tensor memory to be released and resumed later☆271Updated this week
- UniRL is a Framework for Unified Multimodal Model Reinforcement Learning☆913Updated this week
- My learning notes for ML SYS.☆6,936Updated this week
- SGLang-Omni empowers high-performance serving for TTS, ASR, speech and omni models.☆920Updated this week
- APRIL: Active Partial Rollouts in Reinforcement Learning to Tame Long-tail Generation. A system-level optimization for scalable LLM tra…☆61Oct 11, 2025Updated 10 months ago
- Bare Metal GPUs on DigitalOcean Gradient AI • AdPurpose-built for serious AI teams training foundational models, running large-scale inference, and pushing the boundaries of what's possible.
- A Distributed Attention Towards Linear Scalability for Ultra-Long Context, Heterogeneous Data Training☆922Updated this week
- A project implementing various agentic RL based on the Slime post-training framework☆523Apr 11, 2026Updated 4 months ago
- (best/better) practices of megatron on veRL and tuning guide☆138May 12, 2026Updated 3 months ago
- verl Zero-Mismatch Dense/MoE HuggingFace Rollout☆68Aug 5, 2026Updated 2 weeks ago
- A set of examples based on verl for end-to-end RL training recipes.☆324Updated this week
- Distributed Compiler and Optimized Parallel Kernels☆1,520Aug 12, 2026Updated last week
- SkyRL: A Modular Full-stack RL Library for LLMs☆2,188Updated this week
- An Easy-to-use, Scalable and High-performance Agentic RL Framework based on Ray (PPO & DAPO & REINFORCE++ & VLM & TIS & vLLM & Ray & Asy…☆9,947Aug 13, 2026Updated last week
- A NCCL extension library, designed to efficiently offload GPU memory allocated by the NCCL communication library.☆116Dec 17, 2025Updated 8 months ago
- Deploy to Railway using AI coding agents - Free Credits Offer • AdUse Claude Code, Codex, OpenCode, and more. Autonomous software development now has the infrastructure to match with Railway.
- A lightweight, AI-native training framework for large language models. Designed for fast iteration, reproducible experiments, and modular…☆585May 18, 2026Updated 3 months ago
- A flexible and efficient training framework for large-scale alignment tasks☆451Oct 23, 2025Updated 10 months ago
- Miles-diffusion is an post-training framework for large-scale diffusion model training and production workloads, forked from and co-evolv…☆45Updated this week
- A collection of specialized agent skills for AI infrastructure development, enabling Claude Code to write, optimize, and debug high-perfo…☆145Jul 9, 2026Updated last month
- Democratizing Reinforcement Learning for LLMs☆5,796Updated this week
- NexRL is an ultra-loosely-coupled LLM post-training framework.☆118Jul 30, 2026Updated 3 weeks ago
- ☆754Updated this week