Skip to content

Conversation

@xenova
Copy link
Collaborator

@xenova xenova commented Apr 23, 2025

Makes multi-session management much easier, adding a global web inference lock to ensure only one session can run at any given time, preventing "Session has already started" errors.

@HuggingFaceDocBuilderDev

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.

Comment on lines +458 to +460
// Only return the data if it's not a GPU buffer
unpacked.data = tensor.data;
}
Copy link
Collaborator Author

Choose a reason for hiding this comment

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

Needed, otherwise another error is thrown because data is on GPU, not CPU, so we can't access it with .data without awaiting it's contents (not needed for an error message)

@xenova xenova merged commit 6c4fab6 into main Apr 29, 2025
4 checks passed
@xenova xenova deleted the webgpu-fixes branch April 29, 2025 22:43
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