Implementation for FP8/INT8 Rollout for RL training without performence drop.
☆297Nov 7, 2025Updated 5 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:
- ☆244Nov 19, 2025Updated 5 months ago
- An efficient implementation of the NSA (Native Sparse Attention) kernel☆133Jun 24, 2025Updated 10 months ago
- Official implementation for DenseMixer: Improving MoE Post-Training with Precise Router Gradient☆67Aug 3, 2025Updated 9 months ago
- Accelerate LLM preference tuning via prefix sharing with a single line of code☆52Jul 4, 2025Updated 9 months ago
- DeeperGEMM: crazy optimized version☆86May 5, 2025Updated 11 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.
- [ICLR 2025] COAT: Compressing Optimizer States and Activation for Memory-Efficient FP8 Training☆262Aug 9, 2025Updated 8 months ago
- Curse-of-memory phenomenon of RNNs in sequence modelling☆19May 8, 2025Updated 11 months ago
- Fast and memory-efficient exact kmeans☆541Apr 17, 2026Updated 2 weeks ago
- 🔥 LLM-powered GPU kernel synthesis: Train models to convert PyTorch ops into optimized Triton kernels via SFT+RL. Multi-turn compilation…☆136Nov 10, 2025Updated 5 months ago
- Defeating the Training-Inference Mismatch via FP16☆191Nov 14, 2025Updated 5 months ago
- ☆38Aug 7, 2025Updated 8 months ago
- PoC for "SpecReason: Fast and Accurate Inference-Time Compute via Speculative Reasoning" [NeurIPS '25]☆67Oct 2, 2025Updated 7 months ago
- Distributed Compiler based on Triton for Parallel Systems☆1,420Apr 22, 2026Updated last week
- An Efficient and User-Friendly Scaling Library for Reinforcement Learning with Large Language Models☆3,114Updated this week
- 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.
- Code repo for the paper "SpinQuant LLM quantization with learned rotations"☆390Feb 14, 2025Updated last year
- High Performance KV Cache Store for LLM☆53Apr 6, 2026Updated 3 weeks ago
- Bridge Megatron-Core to Hugging Face/Reinforcement Learning☆210Apr 24, 2026Updated last week
- [ICML 2024] BiLLM: Pushing the Limit of Post-Training Quantization for LLMs☆229Jan 11, 2025Updated last year
- [NeurIPS 2025] Scaling Speculative Decoding with Lookahead Reasoning☆68Oct 31, 2025Updated 6 months ago
- 🐳 Efficient Triton implementations for "Native Sparse Attention: Hardware-Aligned and Natively Trainable Sparse Attention"☆993Feb 5, 2026Updated 2 months ago
- The RL Bridge for LLM-based Agent Applications. Made Simple & Flexible.☆5,121Updated this week
- Code and data for paper "(How) do Language Models Track State?"☆22Mar 31, 2025Updated last year
- Fast low-bit matmul kernels in Triton☆445Apr 24, 2026Updated last week
- Managed Kubernetes at scale on DigitalOcean • AdDigitalOcean Kubernetes includes the control plane, bandwidth allowance, container registry, automatic updates, and more for free.
- 🚀 Efficient implementations for emerging model architectures☆4,999Updated this week
- 🎓Automatically Update circult-eda-mlsys-tinyml Papers Daily using Github Actions (Update Every 8th hours)☆10Updated this week
- verl/HybridFlow: A Flexible and Efficient RL Post-Training Framework☆21,046Updated this week
- NVIDIA NVSHMEM is a parallel programming interface for NVIDIA GPUs based on OpenSHMEM. NVSHMEM can significantly reduce multi-process com…☆519Updated this week
- GEAR: An Efficient KV Cache Compression Recipefor Near-Lossless Generative Inference of LLM☆182Jul 12, 2024Updated last year
- [ICLR 2026] RuleReasoner: Reinforced Rule-based Reasoning via Domain-aware Dynamic Sampling☆37Feb 25, 2026Updated 2 months ago
- [ICML 2024] Quest: Query-Aware Sparsity for Efficient Long-Context LLM Inference☆382Jul 10, 2025Updated 9 months ago
- An Easy-to-use, Scalable and High-performance Agentic RL Framework based on Ray (PPO & DAPO & REINFORCE++ & VLM & TIS & vLLM & Ray & Asy…☆9,417Updated this week
- [NeurIPS 2025] The official repo of SynLogic: Synthesizing Verifiable Reasoning Data at Scale for Learning Logical Reasoning and Beyond☆200Jul 7, 2025Updated 9 months ago
- 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.
- ☆52May 19, 2025Updated 11 months ago
- Ring attention implementation with flash attention☆1,014Sep 10, 2025Updated 7 months ago
- [NeurIPS 2024] KVQuant: Towards 10 Million Context Length LLM Inference with KV Cache Quantization☆420Aug 13, 2024Updated last year
- [ICML 2024 Oral] Any-Precision LLM: Low-Cost Deployment of Multiple, Different-Sized LLMs☆125Jul 4, 2025Updated 9 months ago
- slime is an LLM post-training framework for RL Scaling.☆5,490Updated this week
- A collection of specialized agent skills for AI infrastructure development, enabling Claude Code to write, optimize, and debug high-perfo…☆121Apr 15, 2026Updated 2 weeks ago
- APRIL: Active Partial Rollouts in Reinforcement Learning to Tame Long-tail Generation. A system-level optimization for scalable LLM tra…☆57Oct 11, 2025Updated 6 months ago