slime(@slime_framework):Ahead of the upcoming open-source release of GLM-5.3, we’re releasing slime v0.3.2 🚀 Highlights: - Fully aligned GLM-5 training in Megatron with SGLang rollout - Tons of community-contributed bug fixes and optimizations - Continued refactoring and codebase cleanup, including the new slime/observability module - CUDA 13 support Getting slime ready for GLM-5.3 👀

slime

@slime_framework

The LLM post-training framework for RL Scaling.

Joined September 2025

11 Following 2.3K Followers

slime@slime_framework

2026.08.28 02:45

Ahead of the upcoming open-source release of GLM-5.3, we’re releasing slime v0.3.2 🚀 Highlights: - Fully aligned GLM-5 training in Megatron with SGLang rollout - Tons of community-contributed bug fixes and optimizations - Continued refactoring and codebase cleanup, including the new slime/observability module - CUDA 13 support Getting slime ready for GLM-5.3 👀