[Relay] Stop ToMixedPrecision when constant is out of dtype range #15461
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
In some layers, e.g. Clip, we might have a compilation error in the case when operation takes on the input a constant which is out of target data type range. To prevent such situation, a new method was introduced. It compares values of constant attributes with the range of the target data type. In case if the value is out of range then float32 will be used.
|
Thanks for contributing to TVM! Please refer to the contributing guidelines https://tvm.apache.org/docs/contribute/ for useful information and tips. Please request code reviews from Reviewers by @-ing them in a comment. Generated by tvm-bot |
AndrewZhaoLuo
approved these changes
Aug 2, 2023
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Outdated suggestions cannot be applied.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.
In some layers, e.g.
Clip, we might have a compilation error in the case when operation takes on the input a constant which is out of target data type range.To prevent such situation, a new method was introduced. It compares values of constant attributes with the range of the target data type. In case if the value is out of range, then float32 will be used.
cc: @AndrewZhaoLuo, @elvin-n