Async pipelined version of Verl
☆123Apr 8, 2025Updated last year
Alternatives and similar repositories for verl-pipeline
Users that are interested in verl-pipeline are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- Reproducing R1 for Code with Reliable Rewards☆13Apr 9, 2025Updated last year
- ☆83Jun 8, 2026Updated 3 months ago
- Based on the R1-Zero method, using rule-based rewards and GRPO on the Code Contests dataset.☆18Apr 22, 2025Updated last year
- (best/better) practices of megatron on veRL and tuning guide☆138May 12, 2026Updated 4 months ago
- A version of verl to support diverse tool use [TMLR 2026]☆1,041Jul 15, 2026Updated last month
- 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.
- ☆90Aug 16, 2025Updated last year
- SkyRL: A Modular Full-stack RL Library for LLMs☆2,300Updated this week
- ☆37Aug 7, 2025Updated last year
- Democratizing Reinforcement Learning for LLMs☆5,824Updated this week
- [ICLR 2026] End-to-End Reinforcement Learning for Multi-Turn Tool-Integrated Reasoning☆405Mar 30, 2026Updated 5 months ago
- Bridge Megatron-Core to Hugging Face/Reinforcement Learning☆231Jun 15, 2026Updated 3 months ago
- Reproducing R1 for Code with Reliable Rewards☆318May 5, 2025Updated last year
- ☆1,066Jul 14, 2026Updated 2 months ago
- General Reasoner: Advancing LLM Reasoning Across All Domains [NeurIPS25]☆233Nov 27, 2025Updated 9 months ago
- Deploy open-source AI quickly and easily - Special Bonus Offer • AdRunpod Hub is built for open source. One-click deployment and autoscaling endpoints without provisioning your own infrastructure.
- Revisiting Mid-training in the Era of Reinforcement Learning Scaling☆188Jul 23, 2025Updated last year
- Implementation for FP8/INT8 Rollout for RL training without performence drop.☆308Nov 7, 2025Updated 10 months ago
- A scalable asynchronous reinforcement learning implementation with in-flight weight updates.☆432Aug 5, 2026Updated last month
- [COLM 2025] Official repository for R2E-Gym: Procedural Environment Generation and Hybrid Verifiers for Scaling Open-Weights SWE Agents☆334Jul 13, 2025Updated last year
- Scalable RL solution for advanced reasoning of language models☆1,873Mar 18, 2025Updated last year
- Code for Blog Post: Can Better Cold-Start Strategies Improve RL Training for LLMs?☆20Mar 9, 2025Updated last year
- Use the tokenizer in parallel to achieve superior acceleration☆20Mar 21, 2024Updated 2 years ago
- Official repo of dataset-decomposition paper [NeurIPS 2024]☆21Updated this week
- APRIL: Active Partial Rollouts in Reinforcement Learning to Tame Long-tail Generation. A system-level optimization for scalable LLM tra…☆64Oct 11, 2025Updated 11 months ago
- Open source password manager - Proton Pass • AdSecurely store, share, and autofill your credentials with Proton Pass, the end-to-end encrypted password manager trusted by millions.
- Official Repo for Open-Reasoner-Zero☆2,099Jun 2, 2025Updated last year
- NexRL is an ultra-loosely-coupled LLM post-training framework.☆119Updated this week
- Legible, Scalable, Reproducible Foundation Models with Named Tensors and Jax☆16Jun 16, 2024Updated 2 years ago
- The Entropy Mechanism of Reinforcement Learning for Large Language Model Reasoning.☆452Jul 11, 2025Updated last year
- Resources for the Enigmata Project.☆85Aug 13, 2025Updated last year
- Best practices for training DeepSeek, Mixtral, Qwen and other MoE models using Megatron Core.☆201May 29, 2026Updated 3 months ago
- [NeurIPS'24] Official code for *🎯DART-Math: Difficulty-Aware Rejection Tuning for Mathematical Problem-Solving*☆121Dec 10, 2024Updated last year
- Compact and Agent-Native MoE Training System☆350Updated this week
- Code for "[COLM'25] RepoST: Scalable Repository-Level Coding Environment Construction with Sandbox Testing"☆24Mar 18, 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.
- Implementation for "Step-DPO: Step-wise Preference Optimization for Long-chain Reasoning of LLMs"☆397Jan 19, 2025Updated last year
- Unleashing the Power of Reinforcement Learning for Math and Code Reasoners☆738Jun 6, 2025Updated last year
- [ICML 2025] Teaching Language Models to Critique via Reinforcement Learning☆126May 6, 2025Updated last year
- A flexible and efficient training framework for large-scale alignment tasks☆450Oct 23, 2025Updated 10 months ago
- ☆22Aug 26, 2025Updated last year
- Miles is an enterprise-facing reinforcement learning framework for LLM and VLM post-training, forked from and co-evolving with slime.☆2,869Updated this week
- [ICLR 2026] Efficient Agent Training for Computer Use☆145Sep 5, 2025Updated last year