u99127 commented on pull request #6675: URL: https://github.com/apache/incubator-tvm/pull/6675#issuecomment-713901218
> > > dequantize in main branch fails when input is per-channel quantized. There is no bug report. I found this while working on quantizing models in Relay. Cool, could the description above say something like "Fix dequantize for per-channel quantized input" instead of just fixing a bug ? ---------------------------------------------------------------- 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. For queries about this service, please contact Infrastructure at: us...@infra.apache.org
