THUDM / slime

A battle-tested RL post-training framework that unifies Megatron training and SGLang rollout into a single correctness-first pipeline for scalable LLM alignment.

活跃维护 Apache 2.0 Python Tracked
8.3k 1.2k 2 天前
CIPyPI

星标趋势

数据积累中,暂无足够数据生成趋势图

AI 分析

项目摘要

slime is an LLM post-training framework for RL scaling that tightly integrates Megatron for training and SGLang for rollout, providing a unified dataflow for reinforcement learning pipelines. It is battle-tested behind multiple frontier GLM model releases and emphasizes correctness-first infrastructure with flexible data generation capabilities.

为什么值得关注

slime is the RL post-training framework behind GLM-5.2, GLM-5.1, GLM-5, and earlier GLM releases, validating it through complete production-grade training loops rather than isolated examples. Its opinionated design avoids abstraction bloat by natively passing through Megatron and SGLang arguments, making it both lightweight and deeply optimized for large-scale RL.

优势

  • Battle-tested behind multiple frontier GLM model releases, validating full production-grade RL training loops
  • Tight native integration of Megatron training and SGLang rollout without unnecessary abstraction layers
  • Correctness-first design with explicit dataflow, separate rollout-only/train-only debugging paths, and first-class reproducibility

局限性

  • Tightly coupled to Megatron + SGLang ecosystem, limiting flexibility for users on different stacks
  • No Docker support, which may complicate deployment and reproducibility for some teams

使用场景

  • Large-scale RL post-training of language models with custom reward functions and verifiers
  • Training with complex data generation workflows including math, code, search, tools, and multi-agent systems
  • Agentic workflow training with environment interaction and long-horizon rollouts
目标用户: ML engineers and researchers doing RL post-training of large language models at scale, particularly those already using or willing to adopt Megatron and SGLang
学习曲线:
分析模型:LongCat-2.0 | 分析时间:1 个月前