(best/better) practices of megatron on veRL and tuning guide
☆136May 12, 2026Updated last month
Alternatives and similar repositories for verl_megatron_practice
Users that are interested in verl_megatron_practice are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- Bridge Megatron-Core to Hugging Face/Reinforcement Learning☆225Jun 15, 2026Updated 3 weeks ago
- Async pipelined version of Verl☆124Apr 8, 2025Updated last year
- [Archived] For the latest updates and community contribution, please visit: https://github.com/Ascend/TransferQueue or https://gitcode.co…☆16Jan 16, 2026Updated 5 months ago
- [ICLR 2026] End-to-End Reinforcement Learning for Multi-Turn Tool-Integrated Reasoning☆399Mar 30, 2026Updated 3 months ago
- Training library for Megatron-based models with bidirectional Hugging Face conversion capability☆775Updated this week
- AI Agents on 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.
- Evaluating GPT-OSS on BrowseComp-Plus with Native Browsering Tools☆20Oct 17, 2025Updated 8 months ago
- Unleashing the Power of Reinforcement Learning for Math and Code Reasoners☆741Jun 6, 2025Updated last year
- Long Is More for Alignment: A Simple but Tough-to-Beat Baseline for Instruction Fine-Tuning [ICML 2024]☆21May 2, 2024Updated 2 years ago
- ☆90Aug 16, 2025Updated 10 months ago
- Accelerate LLM preference tuning via prefix sharing with a single line of code☆52Jul 4, 2025Updated last year
- ☆31Mar 4, 2024Updated 2 years ago
- Official Repo for Open-Reasoner-Zero☆2,096Jun 2, 2025Updated last year
- Code for "APTBench: Benchmarking Agentic Potential of Base LLMs During Pre-Training"☆42Dec 23, 2025Updated 6 months ago
- FlashTile is a CUDA Tile IR compiler that is compatible with NVIDIA's tileiras, targeting SM70 through SM121 NVIDIA GPUs.☆61Feb 6, 2026Updated 5 months ago
- Simple, predictable pricing with DigitalOcean hosting • AdAlways know what you'll pay with monthly caps and flat pricing. Enterprise-grade infrastructure trusted by 600k+ customers.
- Zero Dependency LibTorch Safetensors Loading and Storing in C++☆23Jul 12, 2024Updated last year
- R1-searcher: Incentivizing the Search Capability in LLMs via Reinforcement Learning☆718Aug 5, 2025Updated 11 months ago
- Implementation for FP8/INT8 Rollout for RL training without performence drop.☆305Nov 7, 2025Updated 8 months ago
- Lightning support for Intel Habana accelerators.☆25Aug 1, 2025Updated 11 months ago
- Train speculative decoding models effortlessly and port them smoothly to SGLang serving.☆967Updated this week
- Composable and Embeddable Communication Runtime for Distributed AI Services☆102Jun 5, 2026Updated last month
- ☆14May 9, 2024Updated 2 years ago
- Sequence-level 1F1B schedule for LLMs.☆37Aug 26, 2025Updated 10 months ago
- Klear-Reasoner: Advancing Reasoning Capability via Gradient-Preserving Clipping Policy Optimization☆82Dec 25, 2025Updated 6 months ago
- Proton VPN Special Offer - Get 70% off • AdSpecial partner offer. Trusted by over 100 million users worldwide. Tested, Approved and Recommended by Experts.
- ☆28Jan 24, 2024Updated 2 years ago
- MultiArchKernelBench: A Multi-Platform Benchmark for Kernel Generation☆59Updated this week
- Exploring the Limit of Outcome Reward for Learning Mathematical Reasoning☆190Mar 20, 2025Updated last year
- ☆1,160Jan 10, 2026Updated 6 months ago
- Official Project Page for HLA: Higher-order Linear Attention (https://arxiv.org/abs/2510.27258)☆102Jun 15, 2026Updated 3 weeks ago
- Engine-agnostic LLM gateway in Rust. Full OpenAI & Anthropic API compatibility across vLLM, TRT-LLM, TokenSpeed, SGLang, OpenAI, Gemini &…☆373Updated this week
- Trinity-RFT is a general-purpose, flexible and scalable framework designed for reinforcement fine-tuning (RFT) of large language models (…☆662Jul 3, 2026Updated last week
- ☆26Nov 20, 2021Updated 4 years ago
- An Easy-to-use, Scalable and High-performance Agentic RL Framework based on Ray (PPO & DAPO & REINFORCE++ & VLM & TIS & vLLM & Ray & Asy…☆9,756Updated 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☆3,281Updated this week
- USP: Unified (a.k.a. Hybrid, 2D) Sequence Parallel Attention for Long Context Transformers Model Training and Inference☆678May 21, 2026Updated last month
- slime is an LLM post-training framework for RL Scaling.☆7,330Updated this week
- 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…☆2,090Jun 9, 2026Updated last month
- Scaling RL on advanced reasoning models☆689Oct 20, 2025Updated 8 months ago
- PSTensor provides a way to hack the memory management of tensors in TensorFlow and PyTorch by defining your own C++ Tensor Class.☆10Feb 10, 2022Updated 4 years ago
- Depict GPU memory footprint during DNN training of PyTorch☆11Nov 17, 2022Updated 3 years ago