Skip to content

GH-3524: Refactor fill_mean_token_embeddings for performance optimization on GPU - #3525

Merged
helpmefindaname merged 3 commits into
flairNLP:masterfrom
sheldon-roberts:optimize-mean-subtoken-pooling
Aug 23, 2024
Merged

helpmefindaname merged 3 commits into
flairNLP:masterfrom
sheldon-roberts:optimize-mean-subtoken-pooling

Conversation

@sheldon-roberts

Copy link
Copy Markdown

#3524

This PR implements the optimization of fill_mean_token_embeddings, as suggested in the linked issue.

@sheldon-roberts
sheldon-roberts force-pushed the optimize-mean-subtoken-pooling branch 2 times, most recently from 59689b2 to dd73547 Compare August 19, 2024 01:29
@sheldon-roberts
sheldon-roberts force-pushed the optimize-mean-subtoken-pooling branch from dd73547 to 4de7940 Compare August 19, 2024 01:30

@helpmefindaname helpmefindaname left a comment

Copy link
Copy Markdown
Member

Choose a reason for hiding this comment

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

Thank you for contributing this,
I could verify that this is way faster than before

@helpmefindaname
helpmefindaname merged commit 7a11174 into flairNLP:master Aug 23, 2024
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

3 participants