fix perf drop in flan-t5 summarization#908
Merged
Merged
Conversation
MohitIntel
requested review from
libinta,
regisss and
yeonsily
and removed request for
regisss
|
The docs for this PR live here. All of your documentation changes will be reflected on that endpoint. The docs are available until 30 days after the last update. |
remove unnecessary pdb
libinta
approved these changes
Apr 22, 2024
regisss
approved these changes
Apr 25, 2024
Collaborator
regisss
left a comment
regisss
left a comment
There was a problem hiding this comment.
LGTM! It also works with 1.15 so merging this now.
ccrhx4
pushed a commit
to ccrhx4/ccrhx4.optimum-habana
that referenced
this pull request
May 11, 2024
Collaborator
3 tasks
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
5 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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Upto 7% performance drop observed in flan-t5 8x summarization task with deepspeed-fork (synapse 1.16 version).
This PR fixes that.