yaof20 / Flash-RLLinks
Implementation for FP8/INT8 Rollout for RL training without performence drop.
☆264Updated last month
Alternatives and similar repositories for Flash-RL
Users that are interested in Flash-RL are comparing it to the libraries listed below
Sorting:
- siiRL: Shanghai Innovation Institute RL Framework for Advanced LLMs and Multi-Agent Systems☆224Updated this week
- Bridge Megatron-Core to Hugging Face/Reinforcement Learning☆149Updated this week
- [ICLR 2025] COAT: Compressing Optimizer States and Activation for Memory-Efficient FP8 Training☆244Updated 3 months ago
- Code for paper: [ICLR2025 Oral] FlexPrefill: A Context-Aware Sparse Attention Mechanism for Efficient Long-Sequence Inference☆151Updated 3 weeks ago
- ☆120Updated 5 months ago
- 🔥 A minimal training framework for scaling FLA models☆286Updated last month
- SeerAttention: Learning Intrinsic Sparse Attention in Your LLMs☆168Updated last month
- Async pipelined version of Verl☆125Updated 7 months ago
- Efficient triton implementation of Native Sparse Attention.☆242Updated 5 months ago
- ☆130Updated 5 months ago
- Super-Efficient RLHF Training of LLMs with Parameter Reallocation☆322Updated 6 months ago
- 🔥 LLM-powered GPU kernel synthesis: Train models to convert PyTorch ops into optimized Triton kernels via SFT+RL. Multi-turn compilation…☆94Updated 3 weeks ago
- A lightweight reinforcement learning framework that integrates seamlessly into your codebase, empowering developers to focus on algorithm…☆68Updated 2 months ago
- Official implementation of "Fast-dLLM: Training-free Acceleration of Diffusion LLM by Enabling KV Cache and Parallel Decoding"☆620Updated 2 weeks ago
- [ICLR2025] Codebase for "ReMoE: Fully Differentiable Mixture-of-Experts with ReLU Routing", built on Megatron-LM.☆97Updated 10 months ago
- Training library for Megatron-based models☆158Updated last week
- (best/better) practices of megatron on veRL and tuning guide☆98Updated last month
- [ICLR 2025] PEARL: Parallel Speculative Decoding with Adaptive Draft Length☆125Updated last week
- LongSpec: Long-Context Lossless Speculative Decoding with Efficient Drafting and Verification☆67Updated 3 months ago
- PoC for "SpecReason: Fast and Accurate Inference-Time Compute via Speculative Reasoning" [NeurIPS '25]☆57Updated last month
- ☆100Updated last month
- ☆95Updated 8 months ago
- Parallel Scaling Law for Language Model — Beyond Parameter and Inference Time Scaling☆450Updated 5 months ago
- Homepage for ProLong (Princeton long-context language models) and paper "How to Train Long-Context Language Models (Effectively)"☆236Updated last month
- Triton implementation of FlashAttention2 that adds Custom Masks.☆146Updated last year
- Official PyTorch implementation of the paper "dLLM-Cache: Accelerating Diffusion Large Language Models with Adaptive Caching" (dLLM-Cache…☆174Updated 2 months ago
- [ICML 2024] Quest: Query-Aware Sparsity for Efficient Long-Context LLM Inference☆344Updated 3 months ago
- [NeurIPS 2025] Simple extension on vLLM to help you speed up reasoning model without training.☆201Updated 5 months ago
- 16-fold memory access reduction with nearly no loss☆106Updated 7 months ago
- MiroRL is an MCP-first reinforcement learning framework for deep research agent.☆170Updated 2 months ago