yaof20 / Flash-RLLinks
Implementation for FP8/INT8 Rollout for RL training without performence drop.
☆281Updated 2 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:
- Bridge Megatron-Core to Hugging Face/Reinforcement Learning☆181Updated this week
- ☆126Updated 7 months ago
- Async pipelined version of Verl☆124Updated 9 months ago
- 🔥 A minimal training framework for scaling FLA models☆333Updated last month
- HuggingFace conversion and training library for Megatron-based models☆324Updated last week
- SeerAttention: Learning Intrinsic Sparse Attention in Your LLMs☆182Updated 3 months ago
- Efficient triton implementation of Native Sparse Attention.☆257Updated 7 months ago
- Code for paper: [ICLR2025 Oral] FlexPrefill: A Context-Aware Sparse Attention Mechanism for Efficient Long-Sequence Inference☆160Updated 2 months ago
- A lightweight reinforcement learning framework that integrates seamlessly into your codebase, empowering developers to focus on algorithm…☆96Updated 4 months ago
- ☆213Updated last month
- ☆133Updated 7 months ago
- [ICLR 2025] COAT: Compressing Optimizer States and Activation for Memory-Efficient FP8 Training☆256Updated 5 months ago
- Super-Efficient RLHF Training of LLMs with Parameter Reallocation☆330Updated 8 months ago
- [ASPLOS'26] Taming the Long-Tail: Efficient Reasoning RL Training with Adaptive Drafter☆121Updated last month
- 🔥 LLM-powered GPU kernel synthesis: Train models to convert PyTorch ops into optimized Triton kernels via SFT+RL. Multi-turn compilation…☆110Updated 2 months ago
- (best/better) practices of megatron on veRL and tuning guide☆114Updated 3 months ago
- [ICLR 2025] PEARL: Parallel Speculative Decoding with Adaptive Draft Length☆144Updated 2 weeks ago
- LongSpec: Long-Context Lossless Speculative Decoding with Efficient Drafting and Verification☆72Updated 5 months ago
- PoC for "SpecReason: Fast and Accurate Inference-Time Compute via Speculative Reasoning" [NeurIPS '25]☆61Updated 3 months ago
- Triton implementation of FlashAttention2 that adds Custom Masks.☆159Updated last year
- [CoLM'25] The official implementation of the paper <MoA: Mixture of Sparse Attention for Automatic Large Language Model Compression>☆153Updated last month
- [ICLR2025] Codebase for "ReMoE: Fully Differentiable Mixture-of-Experts with ReLU Routing", built on Megatron-LM.☆104Updated last year
- ☆102Updated 10 months ago
- Official Implementation of SAM-Decoding: Speculative Decoding via Suffix Automaton☆39Updated 10 months ago
- Ouroboros: Speculative Decoding with Large Model Enhanced Drafting (EMNLP 2024 main)☆113Updated 9 months ago
- 16-fold memory access reduction with nearly no loss☆109Updated 9 months ago
- [ICML 2024] Quest: Query-Aware Sparsity for Efficient Long-Context LLM Inference☆362Updated 6 months ago
- ☆109Updated 3 months ago
- Official PyTorch implementation of the paper "dLLM-Cache: Accelerating Diffusion Large Language Models with Adaptive Caching" (dLLM-Cache…☆191Updated last month
- ☆298Updated 6 months ago