-
Notifications
You must be signed in to change notification settings - Fork 73
API Proposal #5
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.
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
API Proposal #5
Conversation
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
first round
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Great job so far! It's definitely something I'm looking to use in the future.
P.S.: It's my first review on a Kubernetes project, so if I made any mistakes, feel free to let me know.
/assign would like to help review, ping myself for a mark |
/label tide/merge-method-squash |
// services should be consumed by only the backendpool they are part | ||
// of. Should this behavior be breached, routing behavior is not | ||
// guaranteed. | ||
ServiceRef []corev1.ObjectReference |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
It will be set on the httpRoute, this is only to identify the backends.
/lgtm Congratulations! |
[APPROVALNOTIFIER] This PR is APPROVED This pull-request has been approved by: ahg-g, kfswain The full list of commands accepted by this bot can be found here. The pull request process is described here
Needs approval from an approver in each of these files:
Approvers can indicate their approval by writing |
Congrats! |
…odules/golang.org/x/net-0.38.0 Bump golang.org/x/net from 0.37.0 to 0.38.0
* Big ol proposal commit * 1st round of addressing comments * Partial glossary implementation * API updates * glossary additions * adding axioms and faq * Addressing review comments * more proposal updates * clarifying plural modelgroup * editing comment to max col 80 len * More explicit documentation on plural usecases * Adding examples and word clarification * Adding persona summary to ModelGroup obj * Changing Constants to adhere to style guide * Grammatical fixes * Changing BackendPool acronym * CUJ description clarification * Adding back BackendPool with description * Updating names to LLM Service and LLMServerPool * Typos, rewording, and small fixes * another review pass * link fixes * fixing wording, removing duplication * shortining targetmodel name field
This PR contains the initial proposal for what the LLM Instance Gateway API surface might look like. Much of this is rough-in, and expected to change.