Skip to content

@RLsys-Foundation RLsys Foundation

Change the repository type filter

All

    Repositories list

    10 repositories

    • miles

      Public
      Miles is an enterprise-facing reinforcement learning framework for LLM and VLM post-training, forked from and co-evolving with slime.
      Python
      •
      Apache License 2.0
      •108•0•0•0•Updated Jan 27, 2026Jan 27, 2026

    • slime

      Public
      slime is a LLM post-training framework for RL Scaling.
      Python
      •
      Apache License 2.0
      •523•0•0•0•Updated Nov 16, 2025Nov 16, 2025

    • TritonForge

      Public
      🔥 LLM-powered GPU kernel synthesis: Train models to convert PyTorch ops into optimized Triton kernels via SFT+RL. Multi-turn compilation feedback, cross-plat…
      Python
      •2•120•2•0•Updated Nov 10, 2025Nov 10, 2025

    • verl

      Public
      verl: Volcano Engine Reinforcement Learning for LLMs
      Python
      •
      Apache License 2.0
      •3.2k•1•0•0•Updated Oct 23, 2025Oct 23, 2025

    • torch_memory_saver

      Public
      Allow torch tensor memory to be released and resumed later
      Python
      •
      MIT License
      •39•0•0•0•Updated Oct 21, 2025Oct 21, 2025

    • APRIL

      Public
      APRIL: Active Partial Rollouts in Reinforcement Learning to Tame Long-tail Generation. A system-level optimization for scalable LLM training.
      Python
      •
      Apache License 2.0
      •2•48•0•0•Updated Oct 11, 2025Oct 11, 2025

    • RL-Docker-Support

      Public
      Support RL docker images
      0•0•0•0•Updated Oct 11, 2025Oct 11, 2025

    • RLsys-Foundation.github.io

      Public
      doc website for the RLsys-Foundation
      HTML
      •0•0•0•0•Updated Sep 24, 2025Sep 24, 2025

    • sglang

      Public
      SGLang is a fast serving framework for large language models and vision language models.
      Python
      •
      Apache License 2.0
      •4.4k•0•0•0•Updated Sep 21, 2025Sep 21, 2025

    • slime_feature_need

      Public
      Fix these broken features to better support running RL on AMD GPUs
      Python
      •0•0•0•0•Updated Sep 8, 2025Sep 8, 2025