MHarris021 / FT_Llama2

Transformer related optimization, including BERT, GPT

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

FasterTransformer Support for Llama2

About

Transformer related optimization, including BERT, GPT

License:Apache License 2.0


Languages

Language:C++ 67.8%Language:Cuda 28.5%Language:CMake 1.9%Language:Python 1.3%Language:Shell 0.5%Language:Makefile 0.0%Language:C 0.0%Language:HCL 0.0%