TsinghuaAI / InfMoE

Inference framework for MoE layers based on TensorRT with Python binding

Home Page:https://github.com/Harry-Chen/InfMoE

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

InfMoE

InfMoE is currently not stable and under active development. See Harry-Chen/InfMoE for source code & usage.

The code will be available here once officially released.

About

Inference framework for MoE layers based on TensorRT with Python binding

https://github.com/Harry-Chen/InfMoE