rlite-project / RLiteLinks
A lightweight reinforcement learning framework that integrates seamlessly into your codebase, empowering developers to focus on algorithms with minimal intrusion.
☆81Updated 2 months ago
Alternatives and similar repositories for RLite
Users that are interested in RLite are comparing it to the libraries listed below
Sorting:
- Implementation for FP8/INT8 Rollout for RL training without performence drop.☆269Updated 2 weeks ago
- siiRL: Shanghai Innovation Institute RL Framework for Advanced LLMs and Multi-Agent Systems☆226Updated this week
- Odysseus: Playground of LLM Sequence Parallelism☆78Updated last year
- ☆120Updated 5 months ago
- 🔥 LLM-powered GPU kernel synthesis: Train models to convert PyTorch ops into optimized Triton kernels via SFT+RL. Multi-turn compilation…☆99Updated last week
- ☆143Updated this week
- Async pipelined version of Verl☆125Updated 7 months ago
- Accelerate LLM preference tuning via prefix sharing with a single line of code☆51Updated 4 months ago
- Bridge Megatron-Core to Hugging Face/Reinforcement Learning☆159Updated last week
- (best/better) practices of megatron on veRL and tuning guide☆102Updated last month
- ☆95Updated 8 months ago
- ☆199Updated this week
- ☆130Updated 5 months ago
- ☆103Updated 2 months ago
- MiroRL is an MCP-first reinforcement learning framework for deep research agent.☆172Updated 2 months ago
- Towards Economical Inference: Enabling DeepSeek's Multi-Head Latent Attention in Any Transformer-based LLMs☆194Updated last month
- qwen-nsa☆83Updated last month
- [NeurIPS 2024] Fast Best-of-N Decoding via Speculative Rejection☆52Updated last year
- APRIL: Active Partial Rollouts in Reinforcement Learning to Tame Long-tail Generation. A system-level optimization for scalable LLM tra…☆43Updated last month
- ☆86Updated 3 months ago
- Flash-Muon: An Efficient Implementation of Muon Optimizer☆206Updated 5 months ago
- ☆109Updated 6 months ago
- [ICLR 2025] COAT: Compressing Optimizer States and Activation for Memory-Efficient FP8 Training☆249Updated 3 months ago
- Code for paper: [ICLR2025 Oral] FlexPrefill: A Context-Aware Sparse Attention Mechanism for Efficient Long-Sequence Inference☆154Updated last month
- Tiny-FSDP, a minimalistic re-implementation of the PyTorch FSDP☆90Updated 3 months ago
- Ouroboros: Speculative Decoding with Large Model Enhanced Drafting (EMNLP 2024 main)☆112Updated 8 months ago
- Nano repo for RL training of LLMs☆68Updated 3 weeks ago
- Training library for Megatron-based models☆193Updated this week
- Official Implementation of SAM-Decoding: Speculative Decoding via Suffix Automaton☆36Updated 9 months ago
- ☆72Updated 3 weeks ago