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.

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

Adds deployment configuration for extproc #98

Merged
merged 5 commits into from
Jan 16, 2025
Merged

Conversation

mathetake
Copy link
Member

Fixes #82

Copy link
Member Author

@mathetake mathetake left a comment

Choose a reason for hiding this comment

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

Notes

@@ -122,6 +132,45 @@ type LLMRouteRuleMatch struct {
Headers []gwapiv1.HTTPHeaderMatch `json:"headers,omitempty"`
}

type LLMRouteFilterConfig struct {
Copy link
Member Author

Choose a reason for hiding this comment

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

This indirection will help us deprecate and keep the API clean before/after extproc removal per #90

fyi I will work on the compatibility policy doc next

Copy link
Member Author

Choose a reason for hiding this comment

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

Also, this could be AIGatewayFilterConfig per #76

Copy link
Contributor

Choose a reason for hiding this comment

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

right, let's change it all together.

Comment on lines +161 to +169
// Replicas is the number of desired pods of the external process deployment.
//
// +optional
Replicas *int32 `json:"replicas,omitempty"`
// Resources required by the external process container.
// More info: https://kubernetes.io/docs/concepts/configuration/manage-resources-containers/
//
// +optional
Resources *corev1.ResourceRequirements `json:"resources,omitempty"`
Copy link
Member Author

Choose a reason for hiding this comment

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

i could've used either the embedding of appv1.DeploymentSpec or EG's KubernetesDeploymentSpec but both seems too complex for this purpose in addition to the impl cost. we can add additional fields on demand.

@mathetake mathetake marked this pull request as ready for review January 14, 2025 21:25
@mathetake mathetake requested a review from a team as a code owner January 14, 2025 21:25
@mathetake mathetake requested a review from yuzisun January 14, 2025 21:26
Signed-off-by: Takeshi Yoneda <[email protected]>
Signed-off-by: Takeshi Yoneda <[email protected]>
Signed-off-by: Takeshi Yoneda <[email protected]>
@yuzisun
Copy link
Contributor

yuzisun commented Jan 16, 2025

@mathetake there is a conflict to resolve

@mathetake
Copy link
Member Author

aha ok

Signed-off-by: Takeshi Yoneda <[email protected]>
@mathetake mathetake merged commit 47a125e into main Jan 16, 2025
9 checks passed
@mathetake mathetake deleted the filterconfigapi branch January 16, 2025 01:24
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.

Support scaling up ext proc deployment
2 participants