Skip to content

Commit 14b82f8

Browse files
authored
Merge branch 'main' into aaron/fix-doc-quota-policy
2 parents ee34f2c + 1d2f496 commit 14b82f8

3 files changed

Lines changed: 6 additions & 1 deletion

File tree

api/v1alpha1/quota_policy.go

Lines changed: 3 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -42,6 +42,9 @@ type QuotaPolicySpec struct {
4242
// Quota for all models served by AIServiceBackend(s). This value can be overridden for specific models using the "PerModelQuotas"
4343
// configuration.
4444
//
45+
// Currently, the rate limit configuration is properly set up, but the descriptor set is not being set in the Envoy Configuration
46+
// TODO: Add changes in the extension server to support ServiceQuota enforcement.
47+
//
4548
// +optional
4649
ServiceQuota ServiceQuotaDefinition `json:"serviceQuota,omitempty"`
4750
// PerModelQuotas specifies quota for different models served by the AIServiceBackend(s) where this

manifests/charts/ai-gateway-crds-helm/templates/aigateway.envoyproxy.io_quotapolicies.yaml

Lines changed: 2 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -370,6 +370,8 @@ spec:
370370
description: |-
371371
Quota for all models served by AIServiceBackend(s). This value can be overridden for specific models using the "PerModelQuotas"
372372
configuration.
373+
374+
Currently, the rate limit configuration is properly set up, but the descriptor set is not being set in the Envoy Configuration
373375
properties:
374376
costExpression:
375377
description: |-

site/docs/api/api.mdx

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -2338,7 +2338,7 @@ QuotaPolicySpec specifies rules for computing token based costs of requests.
23382338
name="serviceQuota"
23392339
type="[ServiceQuotaDefinition](#github.qkg1.top-envoyproxy-ai-gateway-api-v1alpha1-servicequotadefinition)"
23402340
required="false"
2341-
description="Quota for all models served by AIServiceBackend(s). This value can be overridden for specific models using the `PerModelQuotas`<br />configuration."
2341+
description="Quota for all models served by AIServiceBackend(s). This value can be overridden for specific models using the `PerModelQuotas`<br />configuration.<br />Currently, the rate limit configuration is properly set up, but the descriptor set is not being set in the Envoy Configuration"
23422342
/><ApiField
23432343
name="perModelQuotas"
23442344
type="[PerModelQuota](#github.qkg1.top-envoyproxy-ai-gateway-api-v1alpha1-permodelquota) array"

0 commit comments

Comments
 (0)