Skip to content

Use optimize_module pass for the quantization to fp16 #3874

Use optimize_module pass for the quantization to fp16

Use optimize_module pass for the quantization to fp16 #3874

Triggered via pull request July 21, 2023 03:00
Status Success
Total duration 5h 35m 18s
Artifacts

performance.yaml

on: pull_request
release  /  MIGraphX Performance
1h 40m
release / MIGraphX Performance
Fit to window
Zoom out
Zoom in