Aharrypotter commented on PR #19538: URL: https://github.com/apache/tvm/pull/19538#issuecomment-4535921252
> Before merging, please add a conservative guard for quantized tensors in converters that are not explicitly handled by this PR. Since get_tensors now preserves qnn_params globally, previously unreachable quantized paths can now enter existing non-QDQ converters and may silently produce incorrect IR. For example, SQUARE currently applies R.power directly to the quantized integer tensor instead of DQ -> square -> Q or raising unsupported. > > It would be safer to either: > 1. add QDQ lowering for these ops, or > 2. explicitly raise OpNotImplemented for quantized inputs/outputs in unsupported converters. make sense -- 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]
