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

FEAT: force to specify worker ip and gpu idx when launching models #1195

Merged
merged 5 commits into from
Mar 28, 2024
Merged

FEAT: force to specify worker ip and gpu idx when launching models #1195

merged 5 commits into from
Mar 28, 2024

Conversation

ChengjieLi28
Copy link
Contributor

@ChengjieLi28 ChengjieLi28 commented Mar 27, 2024 •
edited
Loading

  • add --worker-ip and --gpu-idx in launch command line
  • Change the GPU allocation algorithm to maintain the original policy when gpu_idx is not specified, and when gpu_idx is specified, it can be launched as long as the existing model on the GPU is not a vllm model, and there will be a corresponding log.

@XprobeBot XprobeBot added this to the v0.9.5 milestone Mar 27, 2024
@ChengjieLi28 ChengjieLi28 marked this pull request as ready for review March 28, 2024 04:51
qinxuye
qinxuye approved these changes Mar 28, 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 merged commit d9730fb into xorbitsai:main Mar 28, 2024
9 of 12 checks passed
qinxuye pushed a commit to qinxuye/inference that referenced this pull request Apr 2, 2024
@ChengjieLi28 @qinxuye
FEAT: force to specify worker ip and gpu idx when launching models (x…
b10c98b 
…orbitsai#1195)
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
feature gpu
Projects
None yet
Milestone
v0.10.0
Development

Successfully merging this pull request may close these issues.
3 participants
@ChengjieLi28 @qinxuye @XprobeBot