fix ZCH inference input dist error #2682
Closed
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
facebook-github-bot
added
the
CLA Signed
|
This pull request was exported from Phabricator. Differential Revision: D68123290 |
Summary: Serving test failed when ZCH sharding is enabled because embedding lookup request Out of Bound. After compared with training sharding input_dist, found that the keep_orig_idx flag is True when calling training block bucketize kernel, but not set in inference. So this diff is to make that consistent between training and inference, so the ID distribution works the same between training and inference. Reviewed By: kausv Differential Revision: D68123290
emlin
force-pushed
the
export-D68123290
branch
from
e375bea to
d938310
Compare
|
This pull request was exported from Phabricator. Differential Revision: D68123290 |
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Outdated suggestions cannot be applied.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.
Summary:
Serving test failed when ZCH sharding is enabled because embedding lookup request Out of Bound.
After compared with training sharding input_dist, found that the keep_orig_idx flag is True when calling training block bucketize kernel, but not set in inference. So this diff is to make that consistent between training and inference, so the ID distribution works the same between training and inference.
Differential Revision: D68123290