DeepSpeedExamples icon indicating copy to clipboard operation
DeepSpeedExamples copied to clipboard

Published 20 hours ago • verified publisher icon microsoft

Inference test enhance

Open sakogan opened this issue 2 years ago • 0 comments

Allow specifying the number of quantization groups in the inference test script using a quantize_groups argument.

This PR is complimentary to PR #3519 on the main repo, and should be merged with (or after) merging PR #3519.

Tagging @RezaYazdaniAminabadi as a reviewer on #3519.

sakogan avatar Aug 31 '23 20:08 sakogan