An Asynchronous Reinforcement Learning Engine for Omni-Modal Post-Training at Scale
☆622Sep 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.☆151Sep 14, 2026Updated last week
- Official code, data, and models for "Hint Tuning: Less Data Makes Better Reasoners"☆22Jul 8, 2026Updated 2 months ago
- slime is an LLM post-training framework for RL Scaling.☆8,509Updated this week
- Miles is an enterprise-facing reinforcement learning framework for LLM and VLM post-training, forked from and co-evolving with slime.☆2,952Updated this week
- VeOmni: Scaling Any Modality Model Training with Model-Centric Distributed Recipe Zoo☆2,214Updated this week
- Virtual machines for every use case on DigitalOcean • AdGet dependable uptime with 99.99% SLA, simple security tools, and predictable monthly pricing with DigitalOcean's virtual machines, called Droplets.
- An Efficient and User-Friendly Scaling Library for Reinforcement Learning with Large Language Models☆3,401Updated this week
- An LLM post-training framework with vLLM for RL Scaling☆470Updated this week
- The RL Bridge for LLM-based Agent Applications. Made Simple & Flexible.☆5,781Updated this week
- Bridge Megatron-Core to Hugging Face/Reinforcement Learning☆232Jun 15, 2026Updated 3 months ago
- Checkpoint-engine is a simple middleware to update model weights in LLM inference engines☆1,004Updated this week
- An agentic-first RL framework for research (9k lines).☆1,134Updated this week
- Uni-Agent is a framework for training long-horizon agents.☆610Updated this week
- Implementation of an efficient LLM architecture: the Pair-In / Pair-Out Model (PIPO)☆43Jun 10, 2026Updated 3 months ago
- Multimodal RL training framework for diffusion & omni models☆1,075Updated this week
- Managed Database hosting by DigitalOcean • AdPostgreSQL, MySQL, MongoDB, Kafka, Valkey, and OpenSearch available. Automatically scale up storage and focus on building your apps.
- Dataflow-Oriented Reinforcement Learning for (Multi-)Agentic LLMs☆103Jul 26, 2026Updated last month
- Training library for Megatron-based models with bidirectional Hugging Face conversion capability☆921Updated this week
- A high-performance RL training-inference weight synchronization framework, designed to enable second-level parameter updates from trainin …☆176Updated 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 month
- UniRL is a Framework for Unified Multimodal Model Reinforcement Learning☆972Updated this week
- verl/HybridFlow: A Flexible and Efficient RL Post-Training Framework☆23,503Updated this week
- Allow torch tensor memory to be released and resumed later☆275Sep 12, 2026Updated last week
- A Distributed Attention Towards Linear Scalability for Ultra-Long Context, Heterogeneous Data Training☆945Updated this week
- My learning notes for ML SYS.☆7,374Sep 10, 2026Updated last week
- Managed Kubernetes at scale on DigitalOcean • AdDigitalOcean Kubernetes includes the control plane, bandwidth allowance, container registry, automatic updates, and more for free.
- APRIL: Active Partial Rollouts in Reinforcement Learning to Tame Long-tail Generation. A system-level optimization for scalable LLM tra…☆64Oct 11, 2025Updated 11 months ago
- SGLang-Omni is a high-performance serving framework for audio models (TTS, ASR) and unified multimodal models.☆1,235Updated this week
- A project implementing various agentic RL based on the Slime post-training framework☆535Apr 11, 2026Updated 5 months ago
- (best/better) practices of megatron on veRL and tuning guide☆138May 12, 2026Updated 4 months ago
- Distributed Compiler and Optimized Parallel Kernels☆1,547Updated this week
- A lightweight, AI-native training framework for large language models. Designed for fast iteration, reproducible experiments, and modular…☆587Sep 4, 2026Updated 2 weeks ago
- A set of examples based on verl for end-to-end RL training recipes.☆333Updated this week
- verl Zero-Mismatch Dense/MoE HuggingFace Rollout☆74Sep 10, 2026Updated last week
- SkyRL: A Modular Full-stack RL Library for LLMs☆2,334Updated this week
- Managed hosting for WordPress and PHP on Cloudways • AdManaged hosting for WordPress, Magento, Laravel, or PHP apps, on multiple cloud providers. Deploy in minutes on Cloudways by DigitalOcean.
- An Easy-to-use, Scalable and High-performance Agentic RL Framework based on Ray (PPO & DAPO & REINFORCE++ & VLM & TIS & vLLM & Ray & Asy…☆10,020Updated this week
- A NCCL extension library, designed to efficiently offload GPU memory allocated by the NCCL communication library.☆119Dec 17, 2025Updated 9 months ago
- Democratizing Reinforcement Learning for LLMs☆5,829Sep 12, 2026Updated last week
- Agentic RL on Any Harness at Scale☆842Aug 13, 2026Updated last month
- A flexible and efficient training framework for large-scale alignment tasks☆450Oct 23, 2025Updated 10 months ago
- A collection of specialized agent skills for AI infrastructure development, enabling Claude Code to write, optimize, and debug high-perfo…☆147Jul 9, 2026Updated 2 months ago
- HyperEyes is a parallel multimodal search agent that fuses visual grounding and retrieval into a single atomic action, enabling concurren…☆76May 23, 2026Updated 3 months ago