yaof20 / Flash-RLLinks
Implementation for FP8/INT8 Rollout for RL training without performence drop.
☆281Updated 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:
- ☆124Updated 6 months ago
- Code for paper: [ICLR2025 Oral] FlexPrefill: A Context-Aware Sparse Attention Mechanism for Efficient Long-Sequence Inference☆158Updated 2 months ago
- Bridge Megatron-Core to Hugging Face/Reinforcement Learning☆173Updated last week
- 🔥 A minimal training framework for scaling FLA models☆321Updated last month
- ☆207Updated last month
- [ICLR 2025] COAT: Compressing Optimizer States and Activation for Memory-Efficient FP8 Training☆252Updated 4 months ago
- ☆132Updated 6 months ago
- SeerAttention: Learning Intrinsic Sparse Attention in Your LLMs☆177Updated 2 months ago
- Efficient triton implementation of Native Sparse Attention.☆254Updated 6 months ago
- Async pipelined version of Verl☆125Updated 8 months ago
- [ICLR 2025] PEARL: Parallel Speculative Decoding with Adaptive Draft Length☆137Updated last month
- A lightweight reinforcement learning framework that integrates seamlessly into your codebase, empowering developers to focus on algorithm…☆92Updated 3 months ago
- 🔥 LLM-powered GPU kernel synthesis: Train models to convert PyTorch ops into optimized Triton kernels via SFT+RL. Multi-turn compilation…☆107Updated last month
- HuggingFace conversion and training library for Megatron-based models☆270Updated this week
- Super-Efficient RLHF Training of LLMs with Parameter Reallocation☆328Updated 7 months ago
- Official Implementation of SAM-Decoding: Speculative Decoding via Suffix Automaton☆39Updated 10 months ago
- 16-fold memory access reduction with nearly no loss☆109Updated 8 months ago
- [ASPLOS'26] Taming the Long-Tail: Efficient Reasoning RL Training with Adaptive Drafter☆105Updated 2 weeks ago
- PoC for "SpecReason: Fast and Accurate Inference-Time Compute via Speculative Reasoning" [NeurIPS '25]☆60Updated 2 months ago
- APRIL: Active Partial Rollouts in Reinforcement Learning to Tame Long-tail Generation. A system-level optimization for scalable LLM tra…☆44Updated 2 months ago
- ☆107Updated 3 months ago
- [ICML 2025] XAttention: Block Sparse Attention with Antidiagonal Scoring☆256Updated 5 months ago
- ☆293Updated 5 months ago
- ☆112Updated 3 months ago
- LongSpec: Long-Context Lossless Speculative Decoding with Efficient Drafting and Verification☆68Updated 5 months ago
- [CoLM'25] The official implementation of the paper <MoA: Mixture of Sparse Attention for Automatic Large Language Model Compression>☆154Updated 3 weeks ago
- ☆101Updated 9 months ago
- [ICML 2024] Quest: Query-Aware Sparsity for Efficient Long-Context LLM Inference☆357Updated 5 months ago
- Triton implementation of FlashAttention2 that adds Custom Masks.☆155Updated last year
- (best/better) practices of megatron on veRL and tuning guide☆110Updated 2 months ago