rlite-project / RLiteLinks
A lightweight reinforcement learning framework that integrates seamlessly into your codebase, empowering developers to focus on algorithms with minimal intrusion.
☆68Updated 3 weeks 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.☆207Updated last week
- siiRL: Shanghai Innovation Institute RL Framework for Advanced LLMs and Multi-Agent Systems☆211Updated this week
- Odysseus: Playground of LLM Sequence Parallelism☆77Updated last year
- Training library for Megatron-based models☆74Updated this week
- Bridge Megatron-Core to Hugging Face/Reinforcement Learning☆126Updated this week
- ☆126Updated 3 months ago
- ☆119Updated 3 months ago
- Async pipelined version of Verl☆117Updated 5 months ago
- Accelerate LLM preference tuning via prefix sharing with a single line of code☆43Updated 2 months ago
- [ICLR 2025] COAT: Compressing Optimizer States and Activation for Memory-Efficient FP8 Training☆239Updated last month
- ☆92Updated last week
- Skywork-MoE: A Deep Dive into Training Techniques for Mixture-of-Experts Language Models☆137Updated last year
- ☆96Updated 4 months ago
- Flash-Muon: An Efficient Implementation of Muon Optimizer☆185Updated 3 months ago
- MiroRL is an MCP-first reinforcement learning framework for deep research agent.☆154Updated 3 weeks ago
- Nano repo for RL training of LLMs☆65Updated last month
- ☆75Updated last month
- 🔥 A minimal training framework for scaling FLA models☆247Updated last week
- Ouroboros: Speculative Decoding with Large Model Enhanced Drafting (EMNLP 2024 main)☆110Updated 6 months ago
- ☆54Updated 3 months ago
- qwen-nsa☆74Updated 5 months ago
- Official repository for DistFlashAttn: Distributed Memory-efficient Attention for Long-context LLMs Training☆216Updated last year
- Towards Economical Inference: Enabling DeepSeek's Multi-Head Latent Attention in Any Transformer-based LLMs☆188Updated 3 months ago
- Official Implementation of SAM-Decoding: Speculative Decoding via Suffix Automaton☆32Updated 7 months ago
- ☆201Updated 5 months ago
- Efficient Mixture of Experts for LLM Paper List☆127Updated this week
- SeerAttention: Learning Intrinsic Sparse Attention in Your LLMs☆152Updated last month
- (best/better) practices of megatron on veRL and tuning guide☆86Updated 2 weeks ago
- Code for paper: [ICLR2025 Oral] FlexPrefill: A Context-Aware Sparse Attention Mechanism for Efficient Long-Sequence Inference☆141Updated 4 months ago
- Official implementation of ICML 2024 paper "ExCP: Extreme LLM Checkpoint Compression via Weight-Momentum Joint Shrinking".☆48Updated last year