lhutton1 commented on issue #5310: [BYOC] Enhance partitioning and external codegen URL: https://github.com/apache/incubator-tvm/pull/5310#issuecomment-613316418 Apologies, it was bank holiday in the UK :) Although this has now been merged, I've had a look into the constant tensor issue previously and this method of writing out the constant tensor causes very long compilation time for models like VGG16. I couldn't find a nice way to solve this when I was looking into it, but just wanted to raise it here so people are aware. Is this a pattern that we want people to follow in the future?
---------------------------------------------------------------- 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: [email protected] With regards, Apache Git Services
