Enable possibility to not use past_key_values#241
Merged
Conversation
|
The documentation is not available anymore as the PR was closed or merged. |
echarlaix
requested review from
lewtun,
mfuntowicz,
michaelbenayoun and
philschmid
regisss
approved these changes
Jul 12, 2022
Contributor
regisss
left a comment
regisss
left a comment
There was a problem hiding this comment.
It looks great @echarlaix!!
I just left a few nits regarding comments.
philschmid
reviewed
Jul 17, 2022
| ) | ||
| self.encoder_file_name = kwargs.get("last_encoder_model_name", ONNX_ENCODER_NAME) | ||
| self.decoder_file_name = kwargs.get("last_decoder_model_name", ONNX_DECODER_NAME) | ||
| self.decoder_file_with_past_name = kwargs.get("last_decoder_with_past_model_name", ONNX_DECODER_WITH_PAST_NAME) |
Contributor
There was a problem hiding this comment.
We should make this None when there is no past_key model file
Collaborator
Author
There was a problem hiding this comment.
self.use_past_key_values is set to True when a decoder_with_past_session is given, False otherwise (it seems equivalent to what you are suggesting)
Co-authored-by: regisss <15324346+regisss@users.noreply.github.com>
Co-authored-by: regisss <15324346+regisss@users.noreply.github.com>
Co-authored-by: regisss <15324346+regisss@users.noreply.github.com>
…with transformers
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
4 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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
In this PR, we add the possibility to not use the precomputed
past_key_valuesduring ONNX Runtime inference of Seq2Seq models. This can be interesting for small models / short sequence length or if the user don't want to export thedecoder_with_past_model