(best/better) practices of megatron on veRL and tuning guide
☆131Sep 26, 2025Updated 5 months ago
Alternatives and similar repositories for verl_megatron_practice
Users that are interested in verl_megatron_practice are comparing it to the libraries listed below
Sorting:
- Bridge Megatron-Core to Hugging Face/Reinforcement Learning☆197Mar 2, 2026Updated last week
- Async pipelined version of Verl☆124Apr 8, 2025Updated 11 months ago
- [ICLR 2026] End-to-End Reinforcement Learning for Multi-Turn Tool-Integrated Reasoning☆358Jan 12, 2026Updated last month
- FlashTile is a CUDA Tile IR compiler that is compatible with NVIDIA's tileiras, targeting SM70 through SM121 NVIDIA GPUs.☆56Feb 6, 2026Updated last month
- Evaluating GPT-OSS on BrowseComp-Plus with Native Browsering Tools☆17Oct 17, 2025Updated 4 months ago
- Training library for Megatron-based models with bidirectional Hugging Face conversion capability☆481Updated this week
- [Archived] For the latest updates and community contribution, please visit: https://github.com/Ascend/TransferQueue or https://gitcode.co…☆13Jan 16, 2026Updated last month
- Automated GPU Kernel Generation via Co-Evolving Intrinsic World Model☆52Mar 2, 2026Updated last week
- Unleashing the Power of Reinforcement Learning for Math and Code Reasoners☆742Jun 6, 2025Updated 9 months ago
- ☆87Aug 16, 2025Updated 6 months ago
- Official Project Page for HLA: Higher-order Linear Attention (https://arxiv.org/abs/2510.27258)☆45Jan 6, 2026Updated 2 months ago
- Accelerate LLM preference tuning via prefix sharing with a single line of code☆51Jul 4, 2025Updated 8 months ago
- Klear-Reasoner: Advancing Reasoning Capability via Gradient-Preserving Clipping Policy Optimization☆81Dec 25, 2025Updated 2 months ago
- Lightning support for Intel Habana accelerators.☆27Aug 1, 2025Updated 7 months ago
- R1-searcher: Incentivizing the Search Capability in LLMs via Reinforcement Learning☆693Aug 5, 2025Updated 7 months ago
- ☆21Jan 24, 2024Updated 2 years ago
- ☆45Feb 27, 2026Updated last week
- MultiArchKernelBench: A Multi-Platform Benchmark for Kernel Generation☆43Feb 8, 2026Updated last month
- DLSlime: Flexible & Efficient Heterogeneous Transfer Toolkit☆92Jan 26, 2026Updated last month
- verl-agent is an extension of veRL, designed for training LLM/VLM agents via RL. verl-agent is also the official code for paper "Group-in…☆1,611Feb 27, 2026Updated last week
- ☆34Nov 26, 2025Updated 3 months ago
- Implementation for FP8/INT8 Rollout for RL training without performence drop.☆293Nov 7, 2025Updated 4 months ago
- SkyRL: A Modular Full-stack RL Library for LLMs☆1,656Updated this week
- ☆23Nov 20, 2021Updated 4 years ago
- An experimental communicating attention kernel based on DeepEP.☆35Jul 29, 2025Updated 7 months ago
- RewardAnything: Generalizable Principle-Following Reward Models☆45Jun 11, 2025Updated 8 months ago
- An Efficient and User-Friendly Scaling Library for Reinforcement Learning with Large Language Models☆2,919Updated this week
- DeeperGEMM: crazy optimized version☆74May 5, 2025Updated 10 months ago
- A light-weight tool for evaluating LLMs in rule-based ways.☆85Jun 19, 2025Updated 8 months ago
- High Performance Grouped GEMM in PyTorch☆31May 10, 2022Updated 3 years ago
- The repository for ACL 2024 paper "TimeBench: A Comprehensive Evaluation of Temporal Reasoning Abilities in Large Language Models"☆34Jun 29, 2024Updated last year
- Exploring the Limit of Outcome Reward for Learning Mathematical Reasoning☆193Mar 20, 2025Updated 11 months ago
- siiRL: Shanghai Innovation Institute RL Framework for Advanced LLMs and Multi-Agent Systems☆349Jan 30, 2026Updated last month
- Sequence-level 1F1B schedule for LLMs.☆38Aug 26, 2025Updated 6 months ago
- An Easy-to-use, Scalable and High-performance Agentic RL Framework based on Ray (PPO & DAPO & REINFORCE++ & TIS & vLLM & Ray & Async RL)☆9,084Updated this week
- ☆352Jul 29, 2025Updated 7 months ago
- Trinity-RFT is a general-purpose, flexible and scalable framework designed for reinforcement fine-tuning (RFT) of large language models (…☆549Updated this week
- ☆90Jun 30, 2025Updated 8 months ago
- ☆39May 2, 2024Updated last year