[QNN] Fix per-channel broadcast with invalid axes#10936
Merged
Conversation
masahi
changed the title
junrushao
approved these changes
Apr 8, 2022
junrushao
left a comment
junrushao
left a comment
Member
There was a problem hiding this comment.
Thanks for taking swift actions!!
mbrookhart
approved these changes
Apr 8, 2022
pfk-beta
pushed a commit
to pfk-beta/tvm
that referenced
this pull request
Apr 11, 2022
* [QNN] Fix broadcast for invalid axis * broadcast -> channel
mehrdadh
pushed a commit
to mehrdadh/tvm
that referenced
this pull request
Apr 11, 2022
* [QNN] Fix broadcast for invalid axis * broadcast -> channel
altanh
pushed a commit
to altanh/tvm
that referenced
this pull request
Apr 28, 2022
* [QNN] Fix broadcast for invalid axis * broadcast -> channel
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
3 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Per-channel quantization for broadcast ops was supported in #10718, but apparently an invalid
BroadcastAttrscan be created, where the channel axis can be set to 1 even though the input shape is of rank 1. I've hit this error when working on the quantized BERT model with the latestmain. The error can be reproduced by running the test (disabled on CI since it is slow)tvm/tests/python/unittest/test_meta_schedule_integration.py
Line 220 in c2488ac
This PR adds a workaround for cases like that, but I have a feeling that something needs to be fixed on the FQ2I side, where those invalid axes are created.
@sfvaroglu @AndrewZhaoLuo @mbrookhart @anwang2009