File tree Expand file tree Collapse file tree 2 files changed +0
-6
lines changed
config/charts/inferencepool Expand file tree Collapse file tree 2 files changed +0
-6
lines changed Original file line number Diff line number Diff line change 48
48
- " --secure-serving={{ .Values.inferenceExtension.secureServing }}"
49
49
- " --health-checking={{ .Values.inferenceExtension.healthChecking }}"
50
50
- " --cert-path={{ .Values.inferenceExtension.certPath }}"
51
- - " --destination-endpoint-hint-key={{ .Values.inferenceExtension.destinationEndpointHintKey }}"
52
- - " --destination-endpoint-hint-metadata-namespace={{ .Values.inferenceExtension.destinationEndpointHintMetadataNamespace }}"
53
- - " --fairness-id-header-key={{ .Values.inferenceExtension.fairnessIDHeaderKey }}"
54
51
- " --total-queued-requests-metric={{ .Values.inferenceExtension.totalQueuedRequestsMetric }}"
55
52
- " --kv-cache-usage-percentage-metric={{ .Values.inferenceExtension.kvCacheUsagePercentageMetric }}"
56
53
- " --lora-info-metric={{ .Values.inferenceExtension.loraInfoMetric }}"
Original file line number Diff line number Diff line change @@ -14,9 +14,6 @@ inferenceExtension:
14
14
grpcPort : 9002
15
15
grpcHealthPort : 9003
16
16
metricsPort : 9090
17
- destinationEndpointHintMetadataNamespace : " envoy.lb"
18
- destinationEndpointHintKey : " x-gateway-destination-endpoint"
19
- fairnessIDHeaderKey : " x-gateway-inference-fairness-id"
20
17
poolName : " "
21
18
poolNamespace : " default"
22
19
refreshMetricsInterval : " 50ms"
You can’t perform that action at this time.
0 commit comments