Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

ENH: Add guard for model launching #1680

Merged
merged 1 commit into from
Jul 4, 2024
Merged

ENH: Add guard for model launching #1680

merged 1 commit into from
Jul 4, 2024

Conversation

frostyplanet
Copy link
Contributor

@frostyplanet frostyplanet commented Jun 20, 2024 •
edited
Loading 

    worker: Add guard for model launching
    
    Because model launching is a long process (download model, loading into GPU).
    client might encounter network error in the middle while worker is processing,
    add a guard the prevent duplicate operation with the same model_uid.
    
    Provide an rpc call check_model_launch_status() to return LuanchStatus,
    to determine whether worker is still working on this model_uid.

@XprobeBot XprobeBot added this to the v0.12.2 milestone Jun 20, 2024
@frostyplanet frostyplanet force-pushed the launch_guard branch 3 times, most recently from 6b45ceb to 08c4b98 Compare June 24, 2024 09:51
@XprobeBot XprobeBot added the gpu label Jun 24, 2024
@XprobeBot XprobeBot modified the milestones: v0.12.2, v0.12.4 Jun 28, 2024
@frostyplanet frostyplanet force-pushed the launch_guard branch 3 times, most recently from 0022659 to 8a86d63 Compare July 2, 2024 06:56
qinxuye
qinxuye reviewed Jul 2, 2024
View reviewed changes
Copy link
Contributor

@qinxuye qinxuye left a comment

Choose a reason for hiding this comment

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

I left some comments.

xinference/core/worker.py Show resolved Hide resolved
xinference/core/worker.py Outdated Show resolved Hide resolved
xinference/core/worker.py Show resolved Hide resolved
@qinxuye qinxuye changed the title worker: Add guard for model launching ENH: Add guard for model launching Jul 2, 2024
@XprobeBot XprobeBot added the enhancement New feature or request label Jul 2, 2024
qinxuye
qinxuye approved these changes Jul 3, 2024
View reviewed changes
Copy link
Contributor

@qinxuye qinxuye left a comment

Choose a reason for hiding this comment

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

LGTM

@qinxuye qinxuye marked this pull request as draft July 3, 2024 06:54
@frostyplanet
worker: Add guard for model launching
8f845a4 
Because model launching is a long process (download model, loading into GPU).
client might encounter network error in the middle while worker is processing,
add a guard the prevent duplicate operation with the same model_uid.

Provide an rpc call get_model_launch_status() to return LuanchStatus,
to determine whether worker is still working on this model_uid.
@frostyplanet frostyplanet marked this pull request as ready for review July 4, 2024 07:40
@frostyplanet frostyplanet merged commit e99bc6e into xorbitsai:main Jul 4, 2024
12 checks passed
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Reviewers

@qinxuye qinxuye qinxuye approved these changes

Assignees
No one assigned
Labels
enhancement New feature or request gpu
Projects
None yet
Milestone
v0.13.0
Development

Successfully merging this pull request may close these issues.

None yet
3 participants
@frostyplanet @qinxuye @XprobeBot