[Runtime][Python] Convert numpy.uint8 to ABI type i8#24524
Merged
AGindinson merged 1 commit intoMay 26, 2026
Merged
Conversation
AGindinson
approved these changes
May 22, 2026
Contributor
AGindinson
left a comment
AGindinson
left a comment
There was a problem hiding this comment.
Does it make sense to add uint16/uint32, just in case?
maxbartel
changed the title
Signed-off-by: Florian Walbroel <walbroel@roofline.ai>
Manewing
force-pushed
the
walbroel.iree_benchmark_runtime_numpy_uint8_fix
branch
from
1918f94 to
0bb7e7b
Compare
AGindinson
changed the title
AGindinson
approved these changes
May 26, 2026
Contributor
AGindinson
left a comment
AGindinson
left a comment
There was a problem hiding this comment.
LGTM, appreciate the updates!
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Benchmarks are currently failing because of "KeyError: dtype(uint8)" these are fixed by simply converting numpy.uint8 to i8.
Also added other missing data types for numpy, i.e.
uint16anduint32and added a test case to ensure the benchmark argument creation works for all cases