Skip to content

Deprecate inferencepool-resources.yaml #1586

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 3 commits into from
Sep 16, 2025
Merged

Deprecate inferencepool-resources.yaml #1586

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
fa9bd06
Update docs to use helm charts
rahulgurnani Sep 13, 2025
3849af6
Update formatting
rahulgurnani Sep 14, 2025
7553a00
Remove inferencepool resources yaml
rahulgurnani Sep 16, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
186 changes: 0 additions & 186 deletions config/manifests/inferencepool-resources.yaml
View file
Open in desktop

This file was deleted.

10 changes: 3 additions & 7 deletions hack/release-quickstart.sh
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -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"
Expand Down Expand Up @@ -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
Expand Down
39 changes: 17 additions & 22 deletions site-src/implementations/model-servers.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -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.
```