Support the merge of decoder without/with past for encoder-decoder models in the ONNX export #926
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
|
The documentation is not available anymore as the PR was closed or merged. |
fxmarty
requested review from
michaelbenayoun,
JingyaHuang,
regisss and
mht-sharma
and removed request for
michaelbenayoun and
JingyaHuang
4 tasks
michaelbenayoun
approved these changes
Mar 27, 2023
Comment on lines
+624
to
+627
| if self.is_merged is True and self.use_cache_branch is True: | ||
| reference_model_inputs["use_cache_branch"] = DummyInputGenerator.constant_tensor(shape=[1], value=True) | ||
| elif self.is_merged is True and self.use_cache_branch is False: | ||
| reference_model_inputs["use_cache_branch"] = DummyInputGenerator.constant_tensor(shape=[1], value=False) |
There was a problem hiding this comment.
Suggested change
| if self.is_merged is True and self.use_cache_branch is True: | |
| reference_model_inputs["use_cache_branch"] = DummyInputGenerator.constant_tensor(shape=[1], value=True) | |
| elif self.is_merged is True and self.use_cache_branch is False: | |
| reference_model_inputs["use_cache_branch"] = DummyInputGenerator.constant_tensor(shape=[1], value=False) | |
| if self.is_merged: | |
| reference_model_inputs["use_cache_branch"] = DummyInputGenerator.constant_tensor(shape=[1], value=self.use_cache_branch) |
There was a problem hiding this comment.
edit: actually this is less explicit
fxmarty
force-pushed
the
support-encoder-decoder-merge-in-onnx-export
branch
from
9005998 to
8cede08
Compare
fxmarty
force-pushed
the
support-encoder-decoder-merge-in-onnx-export
branch
from
8cede08 to
afb4220
Compare
This was referenced Mar 30, 2023
Closed
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.
As per title, will need #924 to be merged first.
Next PR: support this in ORTModel as well.