rlite-project / RLiteLinks
A lightweight reinforcement learning framework that integrates seamlessly into your codebase, empowering developers to focus on algorithms with minimal intrusion.
☆91Updated 3 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.☆279Updated last month
- Bridge Megatron-Core to Hugging Face/Reinforcement Learning☆168Updated last week
- Async pipelined version of Verl☆125Updated 8 months ago
- 🔥 LLM-powered GPU kernel synthesis: Train models to convert PyTorch ops into optimized Triton kernels via SFT+RL. Multi-turn compilation…☆105Updated last month
- Odysseus: Playground of LLM Sequence Parallelism☆78Updated last year
- MiroRL is an MCP-first reinforcement learning framework for deep research agent.☆182Updated 3 months ago
- ☆122Updated 6 months ago
- Accelerate LLM preference tuning via prefix sharing with a single line of code☆51Updated 5 months ago
- APRIL: Active Partial Rollouts in Reinforcement Learning to Tame Long-tail Generation. A system-level optimization for scalable LLM tra…☆43Updated 2 months ago
- Super-Efficient RLHF Training of LLMs with Parameter Reallocation☆327Updated 7 months ago
- ☆86Updated 3 months ago
- ☆132Updated 6 months ago
- Estimate MFU for DeepSeekV3☆26Updated 11 months ago
- Official Implementation of SAM-Decoding: Speculative Decoding via Suffix Automaton☆38Updated 10 months ago
- ☆203Updated 3 weeks ago
- (best/better) practices of megatron on veRL and tuning guide☆108Updated 2 months ago
- Skywork-MoE: A Deep Dive into Training Techniques for Mixture-of-Experts Language Models☆137Updated last year
- ☆105Updated 3 months ago
- Toolchain built around the Megatron-LM for Distributed Training☆79Updated this week
- Towards Economical Inference: Enabling DeepSeek's Multi-Head Latent Attention in Any Transformer-based LLMs☆197Updated last week
- [NeurIPS 2025] Scaling Speculative Decoding with Lookahead Reasoning☆56Updated last month
- HuggingFace conversion and training library for Megatron-based models☆250Updated this week
- siiRL: Shanghai Innovation Institute RL Framework for Advanced LLMs and Multi-Agent Systems☆304Updated this week
- ☆38Updated this week
- Nano repo for RL training of LLMs☆70Updated last month
- 青稞Talk☆173Updated last week
- ☆208Updated last month
- ☆114Updated 6 months ago
- qwen-nsa☆84Updated last month
- Tiny-FSDP, a minimalistic re-implementation of the PyTorch FSDP☆91Updated 3 months ago