NVIDIA / TransformerEngine

A library for accelerating Transformer models on NVIDIA GPUs, including using 8-bit floating point (FP8) precision on Hopper and Ada GPUs, to provide better performance with lower memory utilization in both training and inference.

https://docs.nvidia.com/deeplearning/transformer-engine/user-guide/index.html

Apache License 2.0

1.61k stars 256 forks source link

Fix TE assert weight error #913

Closed j316chuck closed 3 weeks ago

j316chuck commented 3 weeks ago

Description

Fix TE assert weight error

ksivaman commented 3 weeks ago

Thanks @j316chuck! Could you sign-off your commit? Instructions here.

j316chuck commented 3 weeks ago

Added a sign off 👍