Implementation for FP8/INT8 Rollout for RL training without performence drop.
☆293Nov 7, 2025Updated 3 months ago
Alternatives and similar repositories for Flash-RL
Users that are interested in Flash-RL are comparing it to the libraries listed below
Sorting:
- Fast and memory-efficient exact kmeans☆140Feb 18, 2026Updated last week
- An efficient implementation of the NSA (Native Sparse Attention) kernel☆129Jun 24, 2025Updated 8 months ago
- ☆226Nov 19, 2025Updated 3 months ago
- Code and data for paper "(How) do Language Models Track State?"☆20Mar 31, 2025Updated 11 months ago
- Curse-of-memory phenomenon of RNNs in sequence modelling☆19May 8, 2025Updated 9 months ago
- 🔥 LLM-powered GPU kernel synthesis: Train models to convert PyTorch ops into optimized Triton kernels via SFT+RL. Multi-turn compilation…☆127Nov 10, 2025Updated 3 months ago
- Accelerate LLM preference tuning via prefix sharing with a single line of code☆51Jul 4, 2025Updated 7 months ago
- ☆38Aug 7, 2025Updated 6 months ago
- ☆11Apr 3, 2023Updated 2 years ago
- Defeating the Training-Inference Mismatch via FP16☆182Nov 14, 2025Updated 3 months ago
- [NeurIPS 2025] Scaling Speculative Decoding with Lookahead Reasoning☆67Oct 31, 2025Updated 4 months ago
- Bridge Megatron-Core to Hugging Face/Reinforcement Learning☆197Updated this week
- Official implementation for DenseMixer: Improving MoE Post-Training with Precise Router Gradient☆66Aug 3, 2025Updated 7 months ago
- DeeperGEMM: crazy optimized version☆74May 5, 2025Updated 9 months ago
- [ICLR 2025] COAT: Compressing Optimizer States and Activation for Memory-Efficient FP8 Training☆260Aug 9, 2025Updated 6 months ago
- Distributed Compiler based on Triton for Parallel Systems☆1,371Feb 13, 2026Updated 2 weeks ago
- 🐳 Efficient Triton implementations for "Native Sparse Attention: Hardware-Aligned and Natively Trainable Sparse Attention"☆969Feb 5, 2026Updated 3 weeks ago
- [ICML 2024] Quest: Query-Aware Sparsity for Efficient Long-Context LLM Inference☆374Jul 10, 2025Updated 7 months ago
- [ICML 2024] BiLLM: Pushing the Limit of Post-Training Quantization for LLMs☆228Jan 11, 2025Updated last year
- An Efficient and User-Friendly Scaling Library for Reinforcement Learning with Large Language Models☆2,881Updated this week
- FireQ: Fast INT4-FP8 Kernel and RoPE-aware Quantization for LLM Inference Acceleration☆20Jun 27, 2025Updated 8 months ago
- Lightning-Fast RL for LLM Reasoning and Agents. Made Simple & Flexible.☆3,586Updated this week
- [ICML 2024 Oral] Any-Precision LLM: Low-Cost Deployment of Multiple, Different-Sized LLMs☆122Jul 4, 2025Updated 7 months ago
- 🚀 Efficient implementations of state-of-the-art linear attention models☆4,428Updated this week
- High Performance KV Cache Store for LLM☆47Updated this week
- PoC for "SpecReason: Fast and Accurate Inference-Time Compute via Speculative Reasoning" [NeurIPS '25]☆65Oct 2, 2025Updated 5 months ago
- The evaluation framework for training-free sparse attention in LLMs☆121Jan 27, 2026Updated last month
- APRIL: Active Partial Rollouts in Reinforcement Learning to Tame Long-tail Generation. A system-level optimization for scalable LLM tra…☆51Oct 11, 2025Updated 4 months ago
- Benchmark tests supporting the TiledCUDA library.☆18Nov 19, 2024Updated last year
- [NeurIPS 2025] The official repo of SynLogic: Synthesizing Verifiable Reasoning Data at Scale for Learning Logical Reasoning and Beyond☆194Jul 7, 2025Updated 7 months ago
- [NeurIPS 2024] KVQuant: Towards 10 Million Context Length LLM Inference with KV Cache Quantization☆402Aug 13, 2024Updated last year
- Ring attention implementation with flash attention☆986Sep 10, 2025Updated 5 months ago
- A fast communication-overlapping library for tensor/expert parallelism on GPUs.☆1,261Aug 28, 2025Updated 6 months ago
- [ICML 2023] "Data Efficient Neural Scaling Law via Model Reusing" by Peihao Wang, Rameswar Panda, Zhangyang Wang☆14Jan 4, 2024Updated 2 years ago
- Mamba support for transformer lens☆19Sep 17, 2024Updated last year
- TiledLower is a Dataflow Analysis and Codegen Framework written in Rust.☆14Nov 23, 2024Updated last year
- [ICLR 2026] RuleReasoner: Reinforced Rule-based Reasoning via Domain-aware Dynamic Sampling☆34Updated this week
- PyTorch implementation of the Flash Spectral Transform Unit.☆21Sep 19, 2024Updated last year
- An Easy-to-use, Scalable and High-performance Agentic RL Framework based on Ray (PPO & DAPO & REINFORCE++ & TIS & vLLM & Ray & Async RL)☆9,037Feb 21, 2026Updated last week