Implementation for FP8/INT8 Rollout for RL training without performence drop.
☆308Nov 7, 2025Updated 9 months ago
Alternatives and similar repositories for Flash-RL
Users that are interested in Flash-RL are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- Miles is an enterprise-facing reinforcement learning framework for LLM and VLM post-training, forked from and co-evolving with slime.☆1,956Updated this week
- [ICLR 2026]QeRL enables RL for 32B LLMs on a single H100 GPU.☆513Mar 30, 2026Updated 4 months ago
- Accelerating MoE with IO and Tile-aware Optimizations☆739Jul 4, 2026Updated last month
- APRIL: Active Partial Rollouts in Reinforcement Learning to Tame Long-tail Generation. A system-level optimization for scalable LLM tra…☆60Oct 11, 2025Updated 10 months ago
- SkyRL: A Modular Full-stack RL Library for LLMs☆2,144Updated this week
- 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.
- slime is an LLM post-training framework for RL Scaling.☆7,853Updated this week
- Scaling RL on advanced reasoning models☆692Oct 20, 2025Updated 9 months ago
- Accelerate LLM preference tuning via prefix sharing with a single line of code☆52Jul 4, 2025Updated last year
- Defeating the Training-Inference Mismatch via FP16☆198Nov 14, 2025Updated 8 months ago
- An Efficient and User-Friendly Scaling Library for Reinforcement Learning with Large Language Models☆3,359Updated this week
- Scalable toolkit for efficient model reinforcement☆1,892Updated this week
- verl: Volcano Engine Reinforcement Learning for LLMs☆22Nov 6, 2025Updated 9 months ago
- The RL Bridge for LLM-based Agent Applications. Made Simple & Flexible.☆5,653Updated this week
- Checkpoint-engine is a simple middleware to update model weights in LLM inference engines☆994Aug 5, 2026Updated last week
- Managed Database hosting by DigitalOcean • AdPostgreSQL, MySQL, MongoDB, Kafka, Valkey, and OpenSearch available. Automatically scale up storage and focus on building your apps.
- [NSDI'26] PolyRL is a reinforcement learning framework for LLM that harvest spot instances on the cloud to reduce cost.☆19Mar 30, 2026Updated 4 months ago
- ☆253Nov 19, 2025Updated 8 months ago
- The Entropy Mechanism of Reinforcement Learning for Large Language Model Reasoning.☆449Jul 11, 2025Updated last year
- SPEC-RL: Accelerating On-Policy Reinforcement Learning via Speculative Rollouts☆67Dec 1, 2025Updated 8 months ago
- Long-RL: Scaling RL to Long Sequences (NeurIPS 2025)☆726Sep 24, 2025Updated 10 months ago
- [ICLR 2026] End-to-End Reinforcement Learning for Multi-Turn Tool-Integrated Reasoning☆404Mar 30, 2026Updated 4 months ago
- Democratizing Reinforcement Learning for LLMs☆5,778Updated this week
- [ASPLOS'26] Taming the Long-Tail: Efficient Reasoning RL Training with Adaptive Drafter☆176Feb 27, 2026Updated 5 months ago
- A scalable asynchronous reinforcement learning implementation with in-flight weight updates.☆433Updated this week
- Proton VPN Special Offer - Get 70% off • AdSpecial partner offer. Trusted by over 100 million users worldwide. Tested, Approved and Recommended by Experts.
- 🔥 LLM-powered GPU kernel synthesis: Train models to convert PyTorch ops into optimized Triton kernels via SFT+RL. Multi-turn compilation…☆149Nov 10, 2025Updated 9 months ago
- A version of verl to support diverse tool use [TMLR 2026]☆1,031Jul 15, 2026Updated 3 weeks ago
- Official implementation for DenseMixer: Improving MoE Post-Training with Precise Router Gradient☆68Aug 3, 2025Updated last year
- MiroRL is an MCP-first reinforcement learning framework for deep research agent.☆246Aug 27, 2025Updated 11 months ago
- An efficient implementation of the NSA (Native Sparse Attention) kernel☆134Jun 24, 2025Updated last year
- Agentic RL Training at Scale☆1,887Updated this week
- NexRL is an ultra-loosely-coupled LLM post-training framework.☆118Jul 30, 2026Updated last week
- mKernel: fast multi-node, multi-GPU fused kernels☆264Updated this week
- Efficient Long-context Language Model Training by Core Attention Disaggregation☆106Apr 7, 2026Updated 4 months ago
- Managed hosting for WordPress and PHP on Cloudways • AdManaged hosting for WordPress, Magento, Laravel, or PHP apps, on multiple cloud providers. Deploy in minutes on Cloudways by DigitalOcean.
- 🚀 Efficient implementations for emerging model architectures☆5,543Updated this week
- Compact and Agent-Native MoE Training System☆328Jul 31, 2026Updated last week
- A collection of specialized agent skills for AI infrastructure development, enabling Claude Code to write, optimize, and debug high-perfo…☆142Jul 9, 2026Updated last month
- Train speculative decoding models effortlessly and port them smoothly to SGLang serving.☆1,066Updated this week
- verl/HybridFlow: A Flexible and Efficient RL Post-Training Framework☆22,918Updated this week
- An Ultra-Long Output Reinforcement Learning Approach☆23Jul 31, 2025Updated last year
- ☆361Jul 29, 2025Updated last year