Deprecate inferencepool-resources.yaml (#1586)

* Update docs to use helm charts

* Update formatting

* Remove inferencepool resources yaml

Author: rahulgurnani

config/manifests/inferencepool-resources.yaml

@@ -74,25 +74,21 @@ sed -i.bak "s|kubectl apply -k https://github.com/kubernetes-sigs/gateway-api-in
 # -----------------------------------------------------------------------------
 # Update image references
 # -----------------------------------------------------------------------------
-EPP="config/manifests/inferencepool-resources.yaml"
 #TODO: Put all helm values files into an array to loop over
 EPP_HELM="config/charts/inferencepool/values.yaml"
 BBR_HELM="config/charts/body-based-routing/values.yaml"
 CONFORMANCE_MANIFESTS="conformance/resources/base.yaml"
-echo "Updating ${EPP}, ${EPP_HELM}, ${BBR_HELM}, and ${CONFORMANCE_MANIFESTS} ..."
+echo "Updating ${EPP_HELM}, ${BBR_HELM}, and ${CONFORMANCE_MANIFESTS} ..."
 
 # Update the container tag.
-sed -i.bak -E "s|(us-central1-docker\.pkg\.dev/k8s-staging-images/gateway-api-inference-extension/epp:)[^\"[:space:]]+|\1${RELEASE_TAG}|g" "$EPP"
 sed -i.bak -E "s|(tag: )[^\"[:space:]]+|\1${RELEASE_TAG}|g" "$EPP_HELM"
 sed -i.bak -E "s|(tag: )[^\"[:space:]]+|\1${RELEASE_TAG}|g" "$BBR_HELM"
 sed -i.bak -E "s|(us-central1-docker\.pkg\.dev/k8s-staging-images/gateway-api-inference-extension/epp:)[^\"[:space:]]+|\1${RELEASE_TAG}|g" "$CONFORMANCE_MANIFESTS"
 
 # Update the container image pull policy.
-sed -i.bak '/us-central1-docker.pkg.dev\/k8s-staging-images\/gateway-api-inference-extension\/epp/{n;s/Always/IfNotPresent/;}' "$EPP"
 sed -i.bak '/us-central1-docker.pkg.dev\/k8s-staging-images\/gateway-api-inference-extension\/epp/{n;s/Always/IfNotPresent/;}' "$CONFORMANCE_MANIFESTS"
 
 # Update the container registry.
-sed -i.bak -E "s|us-central1-docker\.pkg\.dev/k8s-staging-images|registry.k8s.io|g" "$EPP"
 sed -i.bak -E "s|us-central1-docker\.pkg\.dev/k8s-staging-images|registry.k8s.io|g" "$EPP_HELM"
 sed -i.bak -E "s|us-central1-docker\.pkg\.dev/k8s-staging-images|registry.k8s.io|g" "$BBR_HELM"
 sed -i.bak -E "s|us-central1-docker\.pkg\.dev/k8s-staging-images|registry.k8s.io|g" "$CONFORMANCE_MANIFESTS"
@@ -139,8 +135,8 @@ sed -i.bak -E "s|us-central1-docker\.pkg\.dev/k8s-staging-images|registry.k8s.io
 # -----------------------------------------------------------------------------
 # Stage the changes
 # -----------------------------------------------------------------------------
-echo "Staging $VERSION_FILE $UPDATED_CRD $README $EPP $EPP_HELM $BBR_HELM $CONFORMANCE_MANIFESTS $VLLM_GPU_DEPLOY $VLLM_CPU_DEPLOY $VLLM_SIM_DEPLOY files..."
-git add $VERSION_FILE $UPDATED_CRD $README $EPP $EPP_HELM $BBR_HELM $CONFORMANCE_MANIFESTS $VLLM_GPU_DEPLOY $VLLM_CPU_DEPLOY $VLLM_SIM_DEPLOY
+echo "Staging $VERSION_FILE $UPDATED_CRD $README $EPP_HELM $BBR_HELM $CONFORMANCE_MANIFESTS $VLLM_GPU_DEPLOY $VLLM_CPU_DEPLOY $VLLM_SIM_DEPLOY files..."
+git add $VERSION_FILE $UPDATED_CRD $README $EPP_HELM $BBR_HELM $CONFORMANCE_MANIFESTS $VLLM_GPU_DEPLOY $VLLM_CPU_DEPLOY $VLLM_SIM_DEPLOY
 
 # -----------------------------------------------------------------------------
 # Cleanup backup files and finish

hack/release-quickstart.sh

@@ -19,34 +19,29 @@ vLLM is configured as the default in the [endpoint picker extension](https://git
 
 Triton specific metric names need to be specified when starting the EPP.
 
-### Option 1: Use Helm
+Use `--set inferencePool.modelServerType=triton-tensorrt-llm` to install the `inferencepool` via helm. See the [`inferencepool` helm guide](https://github.com/kubernetes-sigs/gateway-api-inference-extension/blob/main/config/charts/inferencepool/README.md) for more details.
 
-Use `--set inferencePool.modelServerType=triton-tensorrt-llm` to install the [`inferencepool` via helm](https://github.com/kubernetes-sigs/gateway-api-inference-extension/blob/42eb5ff1c5af1275df43ac384df0ddf20da95134/config/charts/inferencepool). See the [`inferencepool` helm guide](https://github.com/kubernetes-sigs/gateway-api-inference-extension/blob/42eb5ff1c5af1275df43ac384df0ddf20da95134/config/charts/inferencepool/README.md) for more details.
+ Add the following to the `flags` in the helm chart as [flags to EPP](https://github.com/kubernetes-sigs/gateway-api-inference-extension/blob/29ea29028496a638b162ff287c62c0087211bbe5/config/charts/inferencepool/values.yaml#L36)
 
-### Option 2: Edit EPP deployment yaml
-
- Add the following to the `args` of the [EPP deployment](https://github.com/kubernetes-sigs/gateway-api-inference-extension/blob/42eb5ff1c5af1275df43ac384df0ddf20da95134/config/manifests/inferencepool-resources.yaml#L32)
-
- ```
-- --total-queued-requests-metric
-- "nv_trt_llm_request_metrics{request_type=waiting}"
-- --kv-cache-usage-percentage-metric
-- "nv_trt_llm_kv_cache_block_metrics{kv_cache_block_type=fraction}"
-- --lora-info-metric
-- "" # Set an empty metric to disable LoRA metric scraping as they are not supported by Triton yet.
+```
+- name=total-queued-requests-metric
+  value="nv_trt_llm_request_metrics{request_type=waiting}"
+- name=kv-cache-usage-percentage-metric
+  value="nv_trt_llm_kv_cache_block_metrics{kv_cache_block_type=fraction}"
+- name=lora-info-metric
+  value="" # Set an empty metric to disable LoRA metric scraping as they are not supported by Triton yet.
 ```
 
 ## SGLang
 
-### Edit EPP deployment yaml
+ Add the following `flags` while deploying using helm charts in the [EPP deployment](https://github.com/kubernetes-sigs/gateway-api-inference-extension/blob/29ea29028496a638b162ff287c62c0087211bbe5/config/charts/inferencepool/values.yaml#L36)
 
- Add the following to the `args` of the [EPP deployment](https://github.com/kubernetes-sigs/gateway-api-inference-extension/blob/42eb5ff1c5af1275df43ac384df0ddf20da95134/config/manifests/inferencepool-resources.yaml#L32)
 
 ```
-- --totalQueuedRequestsMetric
-- "sglang:num_queue_reqs"
-- --kvCacheUsagePercentageMetric
-- "sglang:token_usage"
-- --lora-info-metric
-- "" # Set an empty metric to disable LoRA metric scraping as they are not supported by SGLang yet.
-```
+- name=total-queued-requests-metric
+  value="sglang:num_queue_reqs"
+- name=kv-cache-usage-percentage-metric
+  value="sglang:token_usage"
+- name=lora-info-metric
+  value="" # Set an empty metric to disable LoRA metric scraping as they are not supported by SGLang yet.
+```