fix: cumsum add_constant bug fix (add dtype for np zeros) #3258
+1
−1
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Outdated suggestions cannot be applied.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.
Description
When compiling the
roberta-base
model from Hugging Face (https://huggingface.co/FacebookAI/roberta-base), aTypeError
occurs in thecumsum
operation. For static shape input, the default datatype ofnp.zeros(new_dims)
function isnp.float64
which is not handled properly by thecreate_constant
utility function.Fixes # (issue)
Reproduction Code:
Type of change
Checklist: