Megatron-MoE-ModelZoo
PublicBest practices for testing advanced Mixtral, DeepSeek, and Qwen series MoE models using Megatron Core MoE.
Creat:2025-03-24T18:46:57
Update:2025-04-02T20:56:50
45
Stars
2
Stars Increase
Best practices for testing advanced Mixtral, DeepSeek, and Qwen series MoE models using Megatron Core MoE.