Skip to content

Conversation

@kaixuanliu
Copy link
Contributor

No description provided.

@kaixuanliu kaixuanliu marked this pull request as ready for review June 25, 2025 08:26
@kaixuanliu
Copy link
Contributor Author

@regisss pls help review. We use our own scripts to do a benchmark, w/ this PR, for model Qwen3/Qwen3-Embedding-8B, the throughput improved from original 121.2 seq/s to 126.93 seq/s

Copy link
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

@regisss regisss merged commit f1df357 into huggingface:main Jun 25, 2025
Signed-off-by: Liu, Kaixuan <[email protected]>
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.

2 participants