as4230 commented on PR #19497: URL: https://github.com/apache/tvm/pull/19497#issuecomment-4365648687
@tlopex I considered going with a dispatch pass like [DispatchSortScan](https://github.com/apache/tvm/blob/main/python/tvm/relax/backend/dispatch_sort_scan.py) but ended up fixing the lowering inline. The CPU and GPU paths here use the same algorithm so adding a separate topi/gpu/ implementation plus dispatch felt like mostly boilerplate and duplication. -- 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] --------------------------------------------------------------------- To unsubscribe, e-mail: [email protected] For additional commands, e-mail: [email protected]
