Skip to content

Conversation

parfeniukink
Copy link
Contributor

  • new CLI parameter allows to control concurrent workers that are generating requests

* new CLI parameter allows to control concurrent workers that are
  generating requests
@parfeniukink parfeniukink self-assigned this Feb 17, 2025
@parfeniukink parfeniukink linked an issue Feb 17, 2025 that may be closed by this pull request
Copy link
Collaborator

@markurtz markurtz left a comment

Choose a reason for hiding this comment

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

@parfeniukink I'm not following the need to add in workers here. We have the configuration settings value for this which is passed through: https://github.com/neuralmagic/guidellm/blob/main/src/guidellm/config.py#L145. What do we gain in adding this and how does it fix the problem listed in the max concurrency off by 1 issue?

@parfeniukink
Copy link
Contributor Author

@parfeniukink I'm not following the need to add in workers here. We have the configuration settings value for this which is passed through: https://github.com/neuralmagic/guidellm/blob/main/src/guidellm/config.py#L145. What do we gain in adding this and how does it fix the problem listed in the max concurrency off by 1 issue?

@markurtz yes, you are correct. This is intermediate implementation that comes out from the discussion. Closing it

@markurtz markurtz deleted the 70-guidellm__max_concurrency-is-off-by-1 branch April 21, 2025 15:02
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.

GUIDELLM__MAX_CONCURRENCY is off by 1

2 participants