[Relax][Bugfix] Preserve dtype in ToMixedPrecision for kNever ops#17263
Merged
tqchen merged 1 commit intoapache:mainfrom Aug 11, 2024
Merged
Conversation
Prior to this commit, while an operator with the `MixedPrecisionPolicyKind::kNever` attribute would not be updated from `float32` to `float16`, it would be erroneously updated from `float16` to `float32`. This commit updates `ToMixedPrecision` to preserve the datatype of any arguments used in a `kNever` operation, rather than forcing them to a `float32` datatype.
tqchen
approved these changes
Aug 11, 2024
Lunderberg
deleted the
relax_bugfix_to_mixed_precision_with_float16_in_input
branch
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
2 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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Prior to this commit, while an operator with the
MixedPrecisionPolicyKind::kNeverattribute would not be updated fromfloat32tofloat16, it would be erroneously updated fromfloat16tofloat32.This commit updates
ToMixedPrecisionto preserve the datatype of any arguments used in akNeveroperation, rather than forcing them to afloat32datatype.