Super-Efficient RLHF Training of LLMs with Parameter Reallocation
☆336Apr 24, 2025Updated last year
Alternatives and similar repositories for ReaLHF
Users that are interested in ReaLHF are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- A Really Scalable RL Framework to 10k+ CPUs☆38Feb 29, 2024Updated 2 years ago
- The RL Bridge for LLM-based Agent Applications. Made Simple & Flexible.☆5,901Updated this week
- A flexible and efficient training framework for large-scale alignment tasks☆451Oct 23, 2025Updated last year
- An Easy-to-use, Scalable and High-performance Agentic RL Framework based on Ray (PPO & DAPO & REINFORCE++ & VLM & TIS & vLLM & Ray & Asy…☆10,142Updated this week
- Exploring the Limit of Outcome Reward for Learning Mathematical Reasoning☆189Mar 20, 2025Updated last year
- 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.
- Ring attention implementation with flash attention☆1,067Sep 10, 2025Updated last year
- Scalable RL solution for advanced reasoning of language models☆1,873Mar 18, 2025Updated last year
- [NSDI'26] PolyRL is a reinforcement learning framework for LLM that harvest spot instances on the cloud to reduce cost.☆19Mar 30, 2026Updated 7 months ago
- An Efficient and User-Friendly Scaling Library for Reinforcement Learning with Large Language Models☆3,447Updated this week
- A scalable asynchronous reinforcement learning implementation with in-flight weight updates.☆439Aug 5, 2026Updated 3 months ago
- Official Repo for Open-Reasoner-Zero☆2,101Jun 2, 2025Updated last year
- Vortex: Programmable Sparse Attention for Agents as Algorithm Designers☆69Aug 22, 2026Updated 2 months ago
- Implementation for FP8/INT8 Rollout for RL training without performence drop.☆309Nov 7, 2025Updated last year
- OpenR: An Open Source Framework for Advanced Reasoning with Large Language Models☆1,859Jan 17, 2025Updated last year
- 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.
- Distributed Compiler and Optimized Parallel Kernels☆1,577Sep 18, 2026Updated last month
- ☆67May 13, 2025Updated last year
- Scalable toolkit for efficient model alignment☆850Oct 6, 2025Updated last year
- Recipes to train reward model for RLHF.☆1,546Apr 24, 2025Updated last year
- Democratizing Reinforcement Learning for LLMs☆5,910Oct 16, 2026Updated 3 weeks ago
- 🐳 Efficient Triton implementations for "Native Sparse Attention: Hardware-Aligned and Natively Trainable Sparse Attention"☆1,025Feb 5, 2026Updated 9 months ago
- A recipe for online RLHF and online iterative DPO.☆544Dec 28, 2024Updated last year
- [ICML 2024] Quest: Query-Aware Sparsity for Efficient Long-Context LLM Inference☆414Jul 10, 2025Updated last year
- slime is an LLM training framework for RL Scaling.☆8,802Updated this week
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- ☆136Nov 11, 2024Updated last year
- [NeurIPS'24] Official code for *🎯DART-Math: Difficulty-Aware Rejection Tuning for Mathematical Problem-Solving*☆120Dec 10, 2024Updated last year
- ☆1,203Jan 10, 2026Updated 9 months ago
- RewardBench: the first evaluation tool for reward models.☆749Oct 14, 2026Updated 3 weeks ago
- Official repository for DistFlashAttn: Distributed Memory-efficient Attention for Long-context LLMs Training☆222Aug 19, 2024Updated 2 years ago
- [ICML 2025] Beyond Bradley-Terry Models: A General Preference Model for Language Model Alignment (https://arxiv.org/abs/2410.02197)☆46Updated this week
- USP: Unified (a.k.a. Hybrid, 2D) Sequence Parallel Attention for Long Context Transformers Model Training and Inference☆696Sep 16, 2026Updated last month
- SkyRL: A Modular Full-stack RL Library for LLMs☆2,498Updated this week
- ReST-MCTS*: LLM Self-Training via Process Reward Guided Tree Search (NeurIPS 2024)☆711Jan 20, 2025Updated last year
- Serverless GPU API endpoints on Runpod - Get Bonus Credits • AdSkip the infrastructure headaches. Auto-scaling, pay-as-you-go, no-ops approach lets you focus on innovating your application.
- ☆335May 31, 2025Updated last year
- ☆813Jun 9, 2025Updated last year
- Bridge Megatron-Core to Hugging Face/Reinforcement Learning☆234Updated this week
- Byted PyTorch Distributed for Hyperscale Training of LLMs and RLs☆1,048Mar 3, 2026Updated 8 months ago
- verl/HybridFlow: A Flexible and Efficient RL Post-Training Framework☆24,154Updated this week
- Repo of paper "Free Process Rewards without Process Labels"☆172Mar 14, 2025Updated last year
- Disaggregated serving system for Large Language Models (LLMs).☆847Apr 6, 2025Updated last year