Yang Yang

Results 2 issues of Yang Yang

enable performance evaluation for tacotron 1

This PR is migrated from gpt-fast [#79](https://github.com/pytorch-labs/gpt-fast/pull/79). We would like to add initial support for Intel GPU in torch-ao with the device option "xpu"(i.e., --device "xpu"). Currently, both BF16 &...

CLA Signed
multibackend