Yan Bai

mbridge. Bridge Megatron-Core to Hugging Face/Reinforcement Learning

verl_megatron_practice. (best/better) practices of megatron on veRL and tuning guide

verl. verl: Volcano Engine Reinforcement Learning for LLMs

Megatron-MoE-ModelZoo. Best practices for testing advanced Mixtral, DeepSeek, and Qwen series MoE models using Megatron Core MoE.

ISEEKYAN.github.io. HTML