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.
Inference framework for MoE layers based on TensorRT with Python binding
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.
Inference framework for MoE layers based on TensorRT with Python binding
https://github.com/Harry-Chen/InfMoE