Update SoftmaxSampling to support dynamic dtypes
#304
Merged
Conversation
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
The output types match the input dtypes passed. And the output schema is computed from the input types passed.
Documentation preview |
karlhigley
approved these changes
Mar 24, 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Outdated suggestions cannot be applied.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.
Update
SoftmaxSamplingto support dynamic dtypes.Currently the output schema of the SoftmaxSampling operator returns static dtypes which does not match the data returned when the operator is called with different dtypes from these.
This update the
compute_output_schemamethod to match the implementation oftransform. It returns ids and scores with the corresponding dtypes of the input ids and scores.Alternatively, we could update the
transformmethod to coerce the outputs to match the static types. However, it feels to me that matching the types passed in could feel more natural, as it would match the behaviour or array and tensor processing libraries, which typically return the same type as came in unless specified explicitly with a cast or extra parameter.