Super-Efficient RLHF Training of LLMs with Parameter Reallocation
☆333Apr 24, 2025Updated 11 months ago
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:
- Lightning-Fast RL for LLM Reasoning and Agents. Made Simple & Flexible.☆4,855Mar 20, 2026Updated last week
- A Really Scalable RL Framework to 10k+ CPUs☆38Feb 29, 2024Updated 2 years ago
- An Easy-to-use, Scalable and High-performance Agentic RL Framework based on Ray (PPO & DAPO & REINFORCE++ & TIS & vLLM & Ray & Async RL)☆9,231Updated this week
- A flexible and efficient training framework for large-scale alignment tasks☆451Oct 23, 2025Updated 5 months ago
- Exploring the Limit of Outcome Reward for Learning Mathematical Reasoning☆193Mar 20, 2025Updated last year
- 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.
- Ring attention implementation with flash attention☆998Sep 10, 2025Updated 6 months ago
- Distributed Compiler based on Triton for Parallel Systems☆1,394Mar 11, 2026Updated 2 weeks ago
- 🐳 Efficient Triton implementations for "Native Sparse Attention: Hardware-Aligned and Natively Trainable Sparse Attention"☆977Feb 5, 2026Updated last month
- Official repository for DistFlashAttn: Distributed Memory-efficient Attention for Long-context LLMs Training☆222Aug 19, 2024Updated last year
- ☆1,113Jan 10, 2026Updated 2 months ago
- verl: Volcano Engine Reinforcement Learning for LLMs☆20,097Updated this week
- A scalable asynchronous reinforcement learning implementation with in-flight weight updates.☆382Updated this week
- Less Is More: Training-Free Sparse Attention with Global Locality for Efficient Reasoning☆29Sep 12, 2025Updated 6 months ago
- Repo of paper "Free Process Rewards without Process Labels"☆170Mar 14, 2025Updated last year
- 1-Click AI Models by DigitalOcean Gradient • AdDeploy popular AI models on DigitalOcean Gradient GPU virtual machines with just a single click and start building anything your business needs.
- Scalable RL solution for advanced reasoning of language models☆1,821Mar 18, 2025Updated last year
- A sparse attention kernel supporting mix sparse patterns☆485Jan 18, 2026Updated 2 months ago
- Official Repo for Open-Reasoner-Zero☆2,086Jun 2, 2025Updated 9 months ago
- Reproducing R1 for Code with Reliable Rewards☆297May 5, 2025Updated 10 months ago
- Disaggregated serving system for Large Language Models (LLMs).☆792Apr 6, 2025Updated 11 months ago
- [ICML 2024] Quest: Query-Aware Sparsity for Efficient Long-Context LLM Inference☆377Jul 10, 2025Updated 8 months ago
- OpenR: An Open Source Framework for Advanced Reasoning with Large Language Models☆1,839Jan 17, 2025Updated last year
- ☆131Nov 11, 2024Updated last year
- [Archived] For the latest updates and community contribution, please visit: https://github.com/Ascend/TransferQueue or https://gitcode.co…☆13Jan 16, 2026Updated 2 months ago
- 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.
- A tiny yet powerful LLM inference system tailored for researching purpose. vLLM-equivalent performance with only 2k lines of code (2% of …☆321Jun 10, 2025Updated 9 months ago
- SkyRL: A Modular Full-stack RL Library for LLMs☆1,713Updated this week
- Code for the paper "VinePPO: Unlocking RL Potential For LLM Reasoning Through Refined Credit Assignment"☆189May 25, 2025Updated 10 months ago
- Scalable toolkit for efficient model alignment☆850Oct 6, 2025Updated 5 months ago
- A recipe for online RLHF and online iterative DPO.☆545Dec 28, 2024Updated last year
- FlashInfer: Kernel Library for LLM Serving☆5,194Updated this week
- An Efficient and User-Friendly Scaling Library for Reinforcement Learning with Large Language Models☆2,989Mar 20, 2026Updated last week
- Mooncake is the serving platform for Kimi, a leading LLM service provided by Moonshot AI.☆4,953Mar 20, 2026Updated last week
- A low-latency & high-throughput serving engine for LLMs☆486Jan 8, 2026Updated 2 months ago
- DigitalOcean Gradient AI Platform • AdBuild production-ready AI agents using customizable tools or access multiple LLMs through a single endpoint. Create custom knowledge bases or connect external data.
- Recipes to train reward model for RLHF.☆1,521Apr 24, 2025Updated 11 months ago
- [NeurIPS'24] Official code for *🎯DART-Math: Difficulty-Aware Rejection Tuning for Mathematical Problem-Solving*☆121Dec 10, 2024Updated last year
- Democratizing Reinforcement Learning for LLMs☆5,259Mar 19, 2026Updated last week
- RewardBench: the first evaluation tool for reward models.☆705Feb 16, 2026Updated last month
- The rule-based evaluation subset and code implementation of Omni-MATH☆27Dec 23, 2024Updated last year
- ☆338May 24, 2025Updated 10 months ago
- A fast communication-overlapping library for tensor/expert parallelism on GPUs.☆1,273Aug 28, 2025Updated 6 months ago