zhber's repositories
FasterTransformer
Transformer related optimization, including BERT, GPT
Language:C++Apache-2.0000
Sparsebit
A model compression and acceleration toolbox based pytorch.
Language:PythonApache-2.0000
TensorRT
TensorRT is a C++ library for high performance inference on NVIDIA GPUs and deep learning accelerators.
Language:C++Apache-2.0000