[BugFix]: select node type error in NarrowDataType pass #10519
Merged
Conversation
This file contains 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
ganler
requested review from
junrushao,
vinx13,
tqchen,
kparzysz-quic,
ZihengJiang,
masahi and
Hzfengsy
as code owners
masahi
approved these changes
Mar 8, 2022
ziqiangxu8457
pushed a commit
to ziqiangxu8457/tvm
that referenced
this pull request
Mar 9, 2022
pfk-beta
pushed a commit
to pfk-beta/tvm
that referenced
this pull request
Apr 11, 2022
This was referenced Apr 12, 2022
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
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Outdated suggestions cannot be applied.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.
Similar issues as:
#10172
#9582
The select node requires that
ture_value.dtype() == false_value.dtype(). While sometimes it is not the case when doing "Narrow Datatype" optimization. This usually happens when we have anargmin/argmaxnode with some other nodes. The workaround is to maketrue_valueandfalse_valuetype-compatible before creating aSelectnode.An artificial ONNX model triggering this bug is attached: model.zip
cc: @masahi