Skip to content

fix perf drop in flan-t5 summarization#908

Merged
regisss merged 2 commits into
mainfrom
mdeopujari/reduce_scatter_fix_flan_t5_perf
Apr 25, 2024
Merged

fix perf drop in flan-t5 summarization#908
regisss merged 2 commits into
mainfrom
mdeopujari/reduce_scatter_fix_flan_t5_perf

Conversation

@MohitIntel
Copy link
Copy Markdown
Contributor

Upto 7% performance drop observed in flan-t5 8x summarization task with deepspeed-fork (synapse 1.16 version).
This PR fixes that.

@MohitIntel MohitIntel requested a review from regisss as a code owner April 19, 2024 21:24
@MohitIntel MohitIntel requested review from libinta, regisss and yeonsily and removed request for regisss April 19, 2024 21:24
@HuggingFaceDocBuilderDev
Copy link
Copy Markdown

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 libinta added the run-test Run CI for PRs from external contributors label Apr 22, 2024
Copy link
Copy Markdown
Collaborator

@regisss regisss left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

LGTM! It also works with 1.15 so merging this now.

@regisss regisss merged commit 4e15cd4 into main Apr 25, 2024
@regisss regisss deleted the mdeopujari/reduce_scatter_fix_flan_t5_perf branch April 25, 2024 16:11
ccrhx4 pushed a commit to ccrhx4/ccrhx4.optimum-habana that referenced this pull request May 11, 2024
@astachowiczhabana
Copy link
Copy Markdown
Collaborator

HabanaAI#173

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

run-test Run CI for PRs from external contributors

Projects

None yet

Development

Successfully merging this pull request may close these issues.

5 participants