zhaoyang-star opened a new issue, #11799: URL: https://github.com/apache/tvm/issues/11799
Hardswish is a common act func in mobilenetv3-large/small and yolov5, etc,. By now this op in QNN will execute dequantize -> fp32 caculate -> quantize. So hardswish int8 impl via LUT is needed. - [ ] P1. Add hardswish int8 impl via LookUpTable -- This is an automated message from the Apache Git Service. To respond to the message, please log on to GitHub and use the URL above to go to the specific comment. To unsubscribe, e-mail: [email protected] For queries about this service, please contact Infrastructure at: [email protected]
