[WIP] Add support for `approx.auto_quantize`

approx-ml / approx

Automatic quantization library

https://approx-ml.github.io/approx/

Apache License 2.0

11 stars 1 forks source link

Closed bushshrub closed 2 years ago

bushshrub commented 2 years ago

This PR adds support for approx.auto_quantize as covered in #16.

This function takes some model (currently only torch module) and returns a quantized version of that model

Also changes the function signature of auto_set_backend() to modify a library variable instead

Closes: #16

May also close #3

bushshrub commented 2 years ago

Blocking, waiting for #22 to hit develop