openpsi-project / ReaLHFView external linksLinks
Super-Efficient RLHF Training of LLMs with Parameter Reallocation
☆331Apr 24, 2025Updated 9 months ago
Alternatives and similar repositories for ReaLHF
Users that are interested in ReaLHF are comparing it to the libraries listed below
Sorting:
- Lightning-Fast RL for LLM Reasoning and Agents. Made Simple & Flexible.☆3,509Updated this week
- A Really Scalable RL Framework to 10k+ CPUs☆38Feb 29, 2024Updated last year
- A flexible and efficient training framework for large-scale alignment tasks☆449Oct 23, 2025Updated 3 months ago
- An Easy-to-use, Scalable and High-performance Agentic RL Framework based on Ray (PPO & DAPO & REINFORCE++ & TIS & vLLM & Ray & Async RL)☆8,989Feb 6, 2026Updated last week
- Exploring the Limit of Outcome Reward for Learning Mathematical Reasoning☆193Mar 20, 2025Updated 10 months ago
- Ring attention implementation with flash attention☆980Sep 10, 2025Updated 5 months ago
- ☆1,088Jan 10, 2026Updated last month
- Distributed Compiler based on Triton for Parallel Systems☆1,350Updated this week
- Code for the paper "VinePPO: Unlocking RL Potential For LLM Reasoning Through Refined Credit Assignment"☆186May 25, 2025Updated 8 months ago
- 🐳 Efficient Triton implementations for "Native Sparse Attention: Hardware-Aligned and Natively Trainable Sparse Attention"☆964Feb 5, 2026Updated last week
- Official repository for DistFlashAttn: Distributed Memory-efficient Attention for Long-context LLMs Training☆222Aug 19, 2024Updated last year
- ☆131Nov 11, 2024Updated last year
- A scalable asynchronous reinforcement learning implementation with in-flight weight updates.☆362Updated this week
- Official Repo for Open-Reasoner-Zero☆2,087Jun 2, 2025Updated 8 months ago
- Less Is More: Training-Free Sparse Attention with Global Locality for Efficient Reasoning☆29Sep 12, 2025Updated 5 months ago
- SkyRL: A Modular Full-stack RL Library for LLMs☆1,571Updated this week
- Disaggregated serving system for Large Language Models (LLMs).☆776Apr 6, 2025Updated 10 months ago
- [ICML 2024] Quest: Query-Aware Sparsity for Efficient Long-Context LLM Inference☆372Jul 10, 2025Updated 7 months ago
- OpenR: An Open Source Framework for Advanced Reasoning with Large Language Models☆1,830Jan 17, 2025Updated last year
- verl: Volcano Engine Reinforcement Learning for LLMs☆19,132Updated this week
- A sparse attention kernel supporting mix sparse patterns☆455Jan 18, 2026Updated 3 weeks ago
- [Archived] For the latest updates and community contribution, please visit: https://github.com/Ascend/TransferQueue or https://gitcode.co…☆13Jan 16, 2026Updated 3 weeks ago
- Reproducing R1 for Code with Reliable Rewards☆286May 5, 2025Updated 9 months ago
- RewardBench: the first evaluation tool for reward models.☆687Jan 31, 2026Updated 2 weeks ago
- [ICML 2025] Beyond Bradley-Terry Models: A General Preference Model for Language Model Alignment (https://arxiv.org/abs/2410.02197)☆39Sep 8, 2025Updated 5 months ago
- Scalable RL solution for advanced reasoning of language models☆1,803Mar 18, 2025Updated 10 months ago
- An Efficient and User-Friendly Scaling Library for Reinforcement Learning with Large Language Models☆2,781Feb 8, 2026Updated last week
- A tiny yet powerful LLM inference system tailored for researching purpose. vLLM-equivalent performance with only 2k lines of code (2% of …☆314Jun 10, 2025Updated 8 months ago
- A low-latency & high-throughput serving engine for LLMs☆474Jan 8, 2026Updated last month
- Repo of paper "Free Process Rewards without Process Labels"☆168Mar 14, 2025Updated 11 months ago
- [NeurIPS'24] Official code for *🎯DART-Math: Difficulty-Aware Rejection Tuning for Mathematical Problem-Solving*☆120Dec 10, 2024Updated last year
- Scalable toolkit for efficient model alignment☆852Oct 6, 2025Updated 4 months ago
- USP: Unified (a.k.a. Hybrid, 2D) Sequence Parallel Attention for Long Context Transformers Model Training and Inference☆643Jan 15, 2026Updated 3 weeks ago
- A recipe for online RLHF and online iterative DPO.☆539Dec 28, 2024Updated last year
- FlashInfer: Kernel Library for LLM Serving☆4,935Updated this week
- O1 Replication Journey☆1,999Jan 14, 2025Updated last year
- AllenAI's post-training codebase☆3,573Updated this week
- Mooncake is the serving platform for Kimi, a leading LLM service provided by Moonshot AI.☆4,701Updated this week
- Recipes to train reward model for RLHF.☆1,512Apr 24, 2025Updated 9 months ago