Updates to remove hacks and add default values file

scaleapi · Nov 1, 2024 · c681522 · c681522
1 parent 21555e8
commit c681522
Show file tree

Hide file tree

Showing 8 changed files with 361 additions and 44 deletions.
diff --git a/charts/model-engine/templates/_helpers.tpl b/charts/model-engine/templates/_helpers.tpl
@@ -341,15 +341,11 @@ env:
     value: "true"
   - name: LAUNCH_SERVICE_TEMPLATE_FOLDER
     value: "/workspace/model-engine/model_engine_server/infra/gateways/resources/templates"
-  {{- if .Values.redis.auth}}
-  - name: REDIS_AUTH_TOKEN
-    value: {{ .Values.redis.auth }}
-  {{- end }}
-  {{- if .Values.redis.authSecret }}
+  {{- if .Values.secrets.kubernetesRedisSecretName }}
   - name: REDIS_AUTH_TOKEN
     valueFrom:
       secretKeyRef:
-        name: {{ .Values.redis.authSecret }}
+        name: {{ .Values.secrets.kubernetesRedisSecretName }}
         key: auth_token
   {{- end }}
   {{- if .Values.azure}}

diff --git a/charts/model-engine/templates/inference_framework_config.yaml b/charts/model-engine/templates/inference_framework_config.yaml
@@ -12,8 +12,8 @@ metadata:
 data:
   deepspeed: "latest"
   text_generation_inference: "latest"
-  vllm: "{{ .Values.vllmTag }}"
-  vllm_batch:  "{{ .Values.vllmTag }}"
-  vllm_batch_v2:  "{{ .Values.vllmTag }}"
+  vllm: "{{ .Values.vLLM.primaryTag }}"
+  vllm_batch:  "{{ .Values.vLLM.batchTag }}"
+  vllm_batch_v2:  "{{ .Values.vLLM.batchV2Tag }}"
   lightllm: "latest"
   tensorrt_llm: "latest"
diff --git a/charts/model-engine/templates/istio-virtualservice.yaml b/charts/model-engine/templates/istio-virtualservice.yaml
@@ -1,12 +1,12 @@
-{{- if .Values.virtualservice.enabled -}}
+{{- if .values.virtualService.enabled -}}
 {{- $fullName := include "modelEngine.fullname" . -}}
 apiVersion: networking.istio.io/v1alpha3
 kind: VirtualService
 metadata:
   name: {{ $fullName }}
   labels:
     {{- include "modelEngine.labels" . | nindent 4 }}
-  {{- with .Values.virtualservice.annotations }}
+  {{- with .values.virtualService.annotations }}
   annotations:
     {{- toYaml . | nindent 4 }}
   {{- end }}

diff --git a/charts/model-engine/templates/service_account_inference.yaml b/charts/model-engine/templates/service_account_inference.yaml
@@ -0,0 +1,25 @@
+{{- if and (.Values.serviceTemplate) (.Values.serviceTemplate.createInferenceServiceAccount) (.Values.serviceTemplate.serviceAccountAnnotations) (.Values.serviceTemplate.serviceAccountName) (.Values.config.values.launch.endpoint_namespace)}}
+{{- $annotations := .Values.serviceTemplate.serviceAccountAnnotations }}
+{{- $inferenceServiceAccountName := .Values.serviceTemplate.serviceAccountName }}
+{{- $inferenceServiceAccountNamespace := .Values.config.values.launch.endpoint_namespace }}
+{{- $labels := include "modelEngine.labels" . }}
+apiVersion: v1
+kind: ServiceAccount
+metadata:
+  name: {{- printf " %s" $inferenceServiceAccountName }}
+  namespace: {{- printf " %s" $inferenceServiceAccountNamespace }}
+  labels:
+    {{- $labels | nindent 4 }}
+  {{- with $annotations }}
+  annotations:
+    {{- toYaml . | nindent 4 }}
+    {{- if $.Values.azure }}
+    azure.workload.identity/client-id: {{ $.Values.azure.client_id }}
+    {{- end }}
+  {{- end }}
+{{- if $.Values.azure }}
+imagePullSecrets:
+  - name: egp-ecr-regcred
+{{- end }}
+---
+{{- end }}
diff --git a/charts/model-engine/templates/service_config_map.yaml b/charts/model-engine/templates/service_config_map.yaml
@@ -64,11 +64,11 @@ data:
 
     sqs_queue_tag_template: |-
       {
-          "infra.scale.com/product": "{{ .Values.productTag }}",
-          "infra.scale.com/team": "${team}",
-          "infra.scale.com/contact": "{{ .Values.contactEmail }}",
-          "infra.scale.com/customer": "AllCustomers",
-          "infra.scale.com/financialOwner": "{{ .Values.contactEmail}}",
+          "{{ .Values.tagging.organization }}/product": "{{ .Values.tagging.productTag }}",
+          "{{ .Values.tagging.organization }}/team": "${team}",
+          "{{ .Values.tagging.organization }}/contact": "{{ .Values.tagging.contactEmail }}",
+          "{{ .Values.tagging.organization }}/customer": "AllCustomers",
+          "{{ .Values.tagging.organization }}/financialOwner": "{{ .Values.tagging.contactEmail }}",
           "Launch-Endpoint-Id": "${endpoint_id}",
           "Launch-Endpoint-Name": "${endpoint_name}",
           "Launch-Endpoint-Created-By": "${endpoint_created_by}"
@@ -101,8 +101,8 @@ data:
     env: {{ .Values.context | quote }}
     cloud_provider: "aws"
     env: "prod"
-    k8s_cluster_name: "usgw1-prod"
-    dns_host_domain: "model-engine.ml-serving.{{ $.Values.global.networking.internalDomain }}"
+    k8s_cluster_name: "{{ .Values.clusterName }}"
+    dns_host_domain: "model-engine.{{ $.Values.global.networking.internalDomain }}"
     default_region: "{{ .Values.aws.region }}"
     ml_account_id: "{{ .Values.aws.accountId }}"
     docker_repo_prefix: "{{ .Values.aws.accountId }}.dkr.ecr.{{ .Values.aws.region }}.amazonaws.com"

diff --git a/charts/model-engine/templates/service_template_config_map.yaml b/charts/model-engine/templates/service_template_config_map.yaml
@@ -95,17 +95,14 @@ data:
             {{- toYaml . | nindent 12 }}
           {{- end }}
           {{- if eq $device "gpu" }}
-          # {{- if empty $node_selector }}
-          # nodeSelector:
-          # {{- end }}
-          #   k8s.amazonaws.com/accelerator: ${GPU_TYPE}
+          {{- if empty $node_selector }}
+          nodeSelector:
+          {{- end }}
+            k8s.amazonaws.com/accelerator: ${GPU_TYPE}
           tolerations:
             - key: "nvidia.com/gpu"
               operator: "Exists"
               effect: "NoSchedule"
-            - key: "gpu_a100_multi"
-              operator: "Exists"
-              effect: "NoSchedule"
           {{- end }}
           priorityClassName: ${PRIORITY}
           containers:
@@ -489,7 +486,7 @@ data:
           protocol: TCP
           name: http
           ${NODE_PORT_DICT}
-  {{- if .Values.virtualservice.enabled }}
+  {{- if .values.virtualService.enabled }}
   virtual-service.yaml: |-
     apiVersion: networking.istio.io/v1alpha3
     kind: VirtualService
@@ -680,17 +677,14 @@ data:
             {{- toYaml . | nindent 12 }}
           {{- end }}
           {{- if eq $device "gpu" }}
-          # {{- if empty $node_selector }}
-          # nodeSelector:
-          # {{- end }}
-          #   k8s.amazonaws.com/accelerator: ${GPU_TYPE}
+          {{- if empty $node_selector }}
+          nodeSelector:
+          {{- end }}
+            k8s.amazonaws.com/accelerator: ${GPU_TYPE}
           tolerations:
             - key: "nvidia.com/gpu"
               operator: "Exists"
               effect: "NoSchedule"
-            - key: "gpu_a100_multi"
-              operator: "Exists"
-              effect: "NoSchedule"
           {{- end }}
           {{- if $service_template_service_account_name }}
           serviceAccountName: {{ $service_template_service_account_name }}