-
Notifications
You must be signed in to change notification settings - Fork 634
deprecate envoy ai gateway and inf extension #12437
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
Changes from all commits
File filter
Filter by extension
Conversations
Jump to
Diff view
Diff view
There are no files selected for viewing
| Original file line number | Diff line number | Diff line change |
|---|---|---|
|
|
@@ -91,9 +91,9 @@ image: | |
|
|
||
| # -- Configure the integration with the Gateway API Inference Extension project, which lets you use kgateway to route to AI inference workloads like LLMs that run locally in your Kubernetes cluster. Documentation for Inference Extension can be found here: https://kgateway.dev/docs/integrations/inference-extension/ | ||
| inferenceExtension: | ||
| # -- Enable Inference Extension. | ||
| # -- Enable Inference Extension. If enabled, agentgateway.enabled should also be set to true. Enabling inference extension without agentgateway is deprecated in v2.1 and will not be supported in v2.2. | ||
|
Member
There was a problem hiding this comment. Choose a reason for hiding this commentThe reason will be displayed to describe this comment to others. Learn more. In the future, is this something we can enforce with a schema definition for the values?
Contributor
Author
There was a problem hiding this comment. Choose a reason for hiding this commentThe reason will be displayed to describe this comment to others. Learn more. Hmm maybe, would need to look into it |
||
| enabled: false | ||
| # -- Enable automatic provisioning for Inference Extension. | ||
| # -- Enable automatic provisioning for Inference Extension. Deprecated: this is deprecated in v2.1 and will be removed in v2.2. | ||
| autoProvision: false | ||
|
|
||
| # -- List of namespace selectors (OR'ed): each entry can use 'matchLabels' or 'matchExpressions' (AND'ed within each entry if used together). Kgateway includes the selected namespaces in config discovery. For more information, see the docs https://kgateway.dev/docs/operations/install/#namespace-discovery. | ||
|
|
||
| Original file line number | Diff line number | Diff line change |
|---|---|---|
|
|
@@ -200,6 +200,7 @@ func buildTranslateFunc( | |
| lambdaFilters: lambdaFilters, | ||
| } | ||
| case v1alpha1.BackendTypeAI: | ||
| logger.Warn("envoy-based AI Gateway is deprecated in v2.1 and will be removed in v2.2. Use agentgateway instead.") | ||
| backendIr.AIIr = &ai.IR{} | ||
| err := ai.PreprocessAIBackend(ctx, i.Spec.AI, backendIr.AIIr) | ||
| if err != nil { | ||
|
|
@@ -361,6 +362,7 @@ func (p *backendPlugin) ApplyForBackend(pCtx *ir.RouteBackendContext, in ir.Http | |
| backendIr := pCtx.Backend.ObjIr.(*BackendIr) | ||
| switch backend.Spec.Type { | ||
| case v1alpha1.BackendTypeAI: | ||
|
|
||
|
Member
There was a problem hiding this comment. Choose a reason for hiding this commentThe reason will be displayed to describe this comment to others. Learn more. nit: remove newline.
Contributor
Author
There was a problem hiding this comment. Choose a reason for hiding this commentThe reason will be displayed to describe this comment to others. Learn more. 👍 can add into my next PR |
||
| err := ai.ApplyAIBackend(backendIr.AIIr, pCtx, out) | ||
| if err != nil { | ||
| return err | ||
|
|
||
Some generated files are not rendered by default. Learn more about how customized files appear on GitHub.
Uh oh!
There was an error while loading. Please reload this page.