deepjavalibrary / djl-serving

A universal scalable machine learning model deployment solution
Apache License 2.0
199 stars 67 forks source link

[lmi][python] remove quantization enum and rely on engine validation/… #2561

Closed siddvenk closed 1 week ago

siddvenk commented 1 week ago

…support

Description

This removes the quantization enum, which we currently rely on for validating the quantization option. We don't really need to be doing this since we can rely directly on the engine for this validation. Furthermore, this enum/validation means we always have to keep the enums up to date. It's more effort than necessary in my opinion.