This repository was archived by the owner on Aug 1, 2023. It is now read-only.
Fix export code after model "hard fork" #667
Closed
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
|
This pull request was exported from Phabricator. Differential Revision: D18648224 |
cndn
added a commit
to cndn/translate
that referenced
this pull request
Nov 23, 2019
Summary: Pull Request resolved: pytorch#667 After internal version is introduced and transformer uses namedtuple instead of dict, need to update the export code accordingly. Also we used torch.empty([0]) to represent initial attention instead of None, to unify the data type in TorchScript. Reviewed By: jhcross Differential Revision: D18648224 fbshipit-source-id: 12a0aaf20162e7fd79d9d4e40cd9deb9ae10ffb7
cndn
force-pushed
the
export-D18648224
branch
from
81e9118 to
96cbe0c
Compare
|
This pull request was exported from Phabricator. Differential Revision: D18648224 |
Summary: Pull Request resolved: pytorch#667 After internal version is introduced and transformer uses namedtuple instead of dict, need to update the export code accordingly. Also we used torch.empty([0]) to represent initial attention instead of None, to unify the data type in TorchScript. Reviewed By: jhcross Differential Revision: D18648224 fbshipit-source-id: b719768e6efad5237fca4c2f7b7e4cf554165f37
cndn
force-pushed
the
export-D18648224
branch
from
96cbe0c to
fad8aca
Compare
|
This pull request was exported from Phabricator. Differential Revision: D18648224 |
caltia
pushed a commit
to caltia/fairseq
that referenced
this pull request
Jul 8, 2025
Summary: Pull Request resolved: pytorch/translate#667 After internal version is introduced and transformer uses namedtuple instead of dict, need to update the export code accordingly. Also we used torch.empty([0]) to represent initial attention instead of None, to unify the data type in TorchScript. Reviewed By: jhcross Differential Revision: D18648224 fbshipit-source-id: efea4252675eae98de24029f18790a7cda8ecdbd
Sign up for free
to subscribe to this conversation on GitHub.
Already have an account?
Sign in.
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.
Summary:
After internal version is introduced and transformer uses namedtuple instead of dict, need to update the export code accordingly.
Also we used torch.empty([0]) to represent initial attention instead of None, to unify the data type in TorchScript.
Differential Revision: D18648224