Zilin Zhu

slime is an LLM post-training framework for RL Scaling.

Miles is an enterprise-facing reinforcement learning framework for LLM and VLM post-training, forked from and co-evolving with slime.

PatrickStar enables Larger, Faster, Greener Pretrained Models for NLP and democratizes AI for everyone.

USP: Unified (a.k.a. Hybrid, 2D) Sequence Parallel Attention for Long Context Transformers Model Training and Inference