feat: make epp-standalone be its own chart

.gitignore

@@ -34,3 +34,9 @@ site
 
 # MacOS generated files
 **/.DS_Store
+
+# Ignore all Chart.lock files anywhere under config/charts
+config/charts/**/Chart.lock
+
+# Ignore all .tgz files anywhere under config/charts
+config/charts/**/*.tgz

config/charts/epp-standalone/.helmignore

@@ -0,0 +1,23 @@
+# Patterns to ignore when building packages.
+# This supports shell glob matching, relative path matching, and
+# negation (prefixed with !). Only one pattern per line.
+.DS_Store
+# Common VCS dirs
+.git/
+.gitignore
+.bzr/
+.bzrignore
+.hg/
+.hgignore
+.svn/
+# Common backup files
+*.swp
+*.bak
+*.tmp
+*.orig
+*~
+# Various IDEs
+.project
+.idea/
+*.tmproj
+.vscode/

config/charts/epp-standalone/Chart.yaml

@@ -0,0 +1,14 @@
+apiVersion: v2
+name: epp-standalone
+description: A Helm chart for Endpoint Picker
+
+type: application
+
+version: 0.0.0
+
+appVersion: "0.0.0"
+
+dependencies:
+  - name: inference-extension
+    version: 0.0.0
+    repository: "file://../inference-extension"

config/charts/epp-standalone/templates/epp-config.yaml

@@ -0,0 +1 @@
+{{- include "inference-extension.config" . -}}

config/charts/epp-standalone/templates/epp-deployment.yaml

@@ -0,0 +1 @@
+{{- include "inference-extension.deployment" . -}}

config/charts/epp-standalone/templates/epp-gke.yaml

@@ -0,0 +1 @@
+{{- include "inference-extension.gke" . -}}

config/charts/epp-standalone/templates/epp-leader-election-rbac.yaml

@@ -0,0 +1 @@
+{{- include "inference-extension.lead-election-rbac" . -}}

config/charts/epp-standalone/templates/epp-rbac.yaml

@@ -0,0 +1 @@
+{{- include "inference-extension.rbac" . -}}

config/charts/epp-standalone/templates/epp-sa-token-secret.yaml

@@ -0,0 +1 @@
+{{- include "inference-extension.sa-token-secret" . -}}

config/charts/epp-standalone/templates/epp-service-monitor.yaml

@@ -0,0 +1 @@
+{{- include "inference-extension.service-monitor" . -}}

config/charts/epp-standalone/templates/epp-service.yaml

@@ -0,0 +1 @@
+{{- include "inference-extension.service" . -}}

config/charts/epp-standalone/values.yaml

@@ -0,0 +1,298 @@
+inferenceExtension:
+  replicas: 1
+  image:
+    name: epp
+    hub: us-central1-docker.pkg.dev/k8s-staging-images/gateway-api-inference-extension
+    tag: main
+    pullPolicy: Always
+  extProcPort: 9002
+  extraServicePorts:
+    - name: http
+      port: 8081
+      protocol: TCP
+      targetPort: 8081
+  env: []
+  pluginsConfigFile: "default-plugins.yaml"
+
+  endpointsServer:
+    standalone: true
+    # Required when standalone is true
+    #    endpointSelector: app=vllm-llama3-8b-instruct
+    targetPorts: 8000
+    modelServerType: vllm # vllm, triton-tensorrt-llm
+
+
+  sidecar:
+    enabled: true
+    configMap:
+      name: envoy
+      # Because the template just dumps this section, the keys become filenames.
+      # The values MUST be strings (note the literal block scalar '|')
+      data:
+        envoy.yaml: |
+          admin:
+            address:
+              socket_address:
+                address: 127.0.0.1
+                port_value: 19000
+            access_log:
+              - name: envoy.access_loggers.file
+                typed_config:
+                  "@type": type.googleapis.com/envoy.extensions.access_loggers.file.v3.FileAccessLog
+                  path: /dev/null
+          static_resources:
+            listeners:
+              - name: envoy-proxy-ready-0.0.0.0-19001
+                address:
+                  socket_address:
+                    address: 0.0.0.0
+                    port_value: 19001
+                filter_chains:
+                  - filters:
+                      - name: envoy.filters.network.http_connection_manager
+                        typed_config:
+                          "@type": type.googleapis.com/envoy.extensions.filters.network.http_connection_manager.v3.HttpConnectionManager
+                          stat_prefix: envoy-ready-http
+                          route_config:
+                            name: local_route
+                            virtual_hosts:
+                              - name: prometheus_stats
+                                domains: ["*"]
+                                routes:
+                                  - match:
+                                      prefix: "/stats/prometheus"
+                                    route:
+                                      cluster: "prometheus_stats"
+                          http_filters:
+                            - name: envoy.filters.http.health_check
+                              typed_config:
+                                "@type": type.googleapis.com/envoy.extensions.filters.http.health_check.v3.HealthCheck
+                                pass_through_mode: false
+                                headers:
+                                  - name: ":path"
+                                    string_match:
+                                      exact: "/ready"
+                            - name: envoy.filters.http.router
+                              typed_config:
+                                "@type": type.googleapis.com/envoy.extensions.filters.http.router.v3.Router
+              - name: vllm
+                address:
+                  socket_address:
+                    address: 0.0.0.0
+                    port_value: 8081
+                per_connection_buffer_limit_bytes: 32768
+                access_log:
+                  - name: envoy.access_loggers.file
+                    filter:
+                      response_flag_filter:
+                        flags: ["NR"]
+                    typed_config:
+                      "@type": type.googleapis.com/envoy.extensions.access_loggers.file.v3.FileAccessLog
+                      path: /dev/stdout
+                      log_format:
+                        text_format_source:
+                          inline_string: "{\"start_time\":\"%START_TIME%\",\"method\":\"%REQ(:METHOD)%\",...}\n"
+                filter_chains:
+                  - name: vllm
+                    filters:
+                      - name: envoy.filters.network.http_connection_manager
+                        typed_config:
+                          "@type": type.googleapis.com/envoy.extensions.filters.network.http_connection_manager.v3.HttpConnectionManager
+                          stat_prefix: http-8081
+                          route_config:
+                            name: vllm
+                            virtual_hosts:
+                              - name: vllm-default
+                                domains: ["*"]
+                                routes:
+                                  - match:
+                                      prefix: "/"
+                                    route:
+                                      cluster: original_destination_cluster
+                                      timeout: 86400s
+                                      idle_timeout: 86400s
+                                      upgrade_configs:
+                                        - upgrade_type: websocket
+                                    typed_per_filter_config:
+                                      envoy.filters.http.ext_proc:
+                                        "@type": type.googleapis.com/envoy.config.route.v3.FilterConfig
+                                        config: {}
+                          http_filters:
+                            - name: envoy.filters.http.ext_proc
+                              typed_config:
+                                "@type": type.googleapis.com/envoy.extensions.filters.http.ext_proc.v3.ExternalProcessor
+                                grpc_service:
+                                  envoy_grpc:
+                                    cluster_name: ext_proc
+                                    authority: localhost:9002
+                                  timeout: 10s
+                                processing_mode:
+                                  request_header_mode: SEND
+                                  response_header_mode: SEND
+                                  request_body_mode: FULL_DUPLEX_STREAMED
+                                  response_body_mode: FULL_DUPLEX_STREAMED
+                                  request_trailer_mode: SEND
+                                  response_trailer_mode: SEND
+                                message_timeout: 1000s
+                            - name: envoy.filters.http.router
+                              typed_config:
+                                "@type": type.googleapis.com/envoy.extensions.filters.http.router.v3.Router
+                                suppress_envoy_headers: true
+                          http2_protocol_options:
+                            max_concurrent_streams: 100
+                            initial_stream_window_size: 65536
+                            initial_connection_window_size: 1048576
+                          use_remote_address: true
+                          normalize_path: true
+                          merge_slashes: true
+                          server_header_transformation: PASS_THROUGH
+                          common_http_protocol_options:
+                            headers_with_underscores_action: REJECT_REQUEST
+                          path_with_escaped_slashes_action: UNESCAPE_AND_REDIRECT
+                          access_log:
+                            - name: envoy.access_loggers.file
+                              typed_config:
+                                "@type": type.googleapis.com/envoy.extensions.access_loggers.file.v3.FileAccessLog
+                                path: /dev/stdout
+                                log_format:
+                                  text_format_source:
+                                    inline_string: "{\"start_time\":\"%START_TIME%\",\"method\":\"%REQ(:METHOD)%\",...}\n"
+            clusters:
+              - name: prometheus_stats
+                type: STATIC
+                connect_timeout: 0.250s
+                load_assignment:
+                  cluster_name: prometheus_stats
+                  endpoints:
+                    - lb_endpoints:
+                        - endpoint:
+                            address:
+                              socket_address:
+                                address: 127.0.0.1
+                                port_value: 19000
+              - name: original_destination_cluster
+                type: ORIGINAL_DST
+                connect_timeout: 1000s
+                lb_policy: CLUSTER_PROVIDED
+                circuit_breakers:
+                  thresholds:
+                    - max_connections: 40000
+                      max_pending_requests: 40000
+                      max_requests: 40000
+                original_dst_lb_config:
+                  use_http_header: true
+                  http_header_name: x-gateway-destination-endpoint
+              - name: ext_proc
+                type: STATIC
+                connect_timeout: 86400s
+                lb_policy: LEAST_REQUEST
+                circuit_breakers:
+                  thresholds:
+                    - max_connections: 40000
+                      max_pending_requests: 40000
+                      max_requests: 40000
+                      max_retries: 1024
+                health_checks:
+                  - timeout: 2s
+                    interval: 10s
+                    unhealthy_threshold: 3
+                    healthy_threshold: 2
+                    reuse_connection: true
+                    grpc_health_check:
+                      service_name: "envoy.service.ext_proc.v3.ExternalProcessor"
+                    tls_options:
+                      alpn_protocols: ["h2"]
+                transport_socket:
+                  name: "envoy.transport_sockets.tls"
+                  typed_config:
+                    "@type": type.googleapis.com/envoy.extensions.transport_sockets.tls.v3.UpstreamTlsContext
+                    common_tls_context:
+                      validation_context:
+                typed_extension_protocol_options:
+                  envoy.extensions.upstreams.http.v3.HttpProtocolOptions:
+                    "@type": type.googleapis.com/envoy.extensions.upstreams.http.v3.HttpProtocolOptions
+                    explicit_http_config:
+                      http2_protocol_options:
+                        initial_stream_window_size: 65536
+                        initial_connection_window_size: 1048576
+                load_assignment:
+                  cluster_name: ext_proc
+                  endpoints:
+                    - locality:
+                        region: ext_proc/e2e/0
+                      lb_endpoints:
+                        - endpoint:
+                            address:
+                              socket_address:
+                                address: 127.0.0.1
+                                port_value: 9002
+                          load_balancing_weight: 1
+    name: envoy-sidecar
+    image: docker.io/envoyproxy/envoy:distroless-v1.33.2
+    command: "envoy"
+    args:
+      - "--service-node"
+      - "envoy-sidecar"
+      - "--log-level"
+      - "trace"
+      - "--cpuset-threads"
+      - "--drain-strategy"
+      - "immediate"
+      - "--drain-time-s"
+      - "60"
+      - "-c"
+      - "/etc/envoy/envoy.yaml"
+    env:
+      - name: NS_NAME
+        valueFrom:
+          fieldRef:
+            fieldPath: metadata.namespace
+      - name: POD_NAME
+        valueFrom:
+          fieldRef:
+            fieldPath: metadata.name
+    ports:
+      - containerPort: 8081
+        name: http-8081
+      - containerPort: 19001
+        name: metrics-19001
+    resources:
+      requests:
+        cpu: 100m
+        memory: 512Mi
+
+    readinessProbe:
+      failureThreshold: 1
+      httpGet:
+        path: /ready
+        port: 19001
+        scheme: HTTP
+      periodSeconds: 5
+      successThreshold: 1
+      timeoutSeconds: 1
+
+    volumeMounts:
+      - name: config
+        mountPath: /etc/envoy
+        readOnly: true
+    volumes:
+      - name: config
+        configMap:
+          name: envoy
+          items:
+            - key: envoy.yaml
+              path: envoy.yaml
+  monitoring:
+    interval: "10s"
+    # Prometheus ServiceMonitor will be created when enabled for EPP metrics collection
+    prometheus:
+      enabled: false
+      auth:
+        # To allow unauthenticated /metrics access (e.g., for debugging with curl), set to false
+        enabled: true
+
+  tracing:
+    enabled: false
+
+  latencyPredictor:
+    enabled: false

config/charts/inference-extension/.helmignore

@@ -0,0 +1,23 @@
+# Patterns to ignore when building packages.
+# This supports shell glob matching, relative path matching, and
+# negation (prefixed with !). Only one pattern per line.
+.DS_Store
+# Common VCS dirs
+.git/
+.gitignore
+.bzr/
+.bzrignore
+.hg/
+.hgignore
+.svn/
+# Common backup files
+*.swp
+*.bak
+*.tmp
+*.orig
+*~
+# Various IDEs
+.project
+.idea/
+*.tmproj
+.vscode/

config/charts/inference-extension/Chart.yaml

@@ -0,0 +1,10 @@
+apiVersion: v2
+name: inference-extension
+description: A library Helm chart for Endpoint Picker
+
+type: library
+
+version: 0.0.0
+
+appVersion: "0.0.0"
+