-
Notifications
You must be signed in to change notification settings - Fork 83
Fix Image Loading for Podman in E2E Tests #377
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.
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
base: main
Are you sure you want to change the base?
Changes from all commits
e49111e
a7bcad2
8f620c5
40a7a90
40e875e
4794998
2d376a2
5a23fdc
f333244
399d919
File filter
Filter by extension
Conversations
Jump to
Diff view
Diff view
There are no files selected for viewing
Original file line number | Diff line number | Diff line change |
---|---|---|
|
@@ -18,7 +18,3 @@ resources: | |
- deployments.yaml | ||
- gateways.yaml | ||
- httproutes.yaml | ||
|
||
images: | ||
- name: ghcr.io/llm-d/llm-d-inference-scheduler | ||
newTag: ${EPP_TAG} | ||
There was a problem hiding this comment. Choose a reason for hiding this commentThe reason will be displayed to describe this comment to others. Learn more. Please undo this change. The file as it was allows the YAML file to be used outside of the kind based tests. |
Original file line number | Diff line number | Diff line change |
---|---|---|
|
@@ -17,7 +17,7 @@ spec: | |
spec: | ||
containers: | ||
- name: vllm | ||
image: ghcr.io/llm-d/llm-d-inference-sim:latest | ||
image: ${VLLM_SIMULATOR_IMAGE} | ||
imagePullPolicy: IfNotPresent | ||
args: | ||
- "--port=8000" | ||
|
@@ -49,7 +49,7 @@ spec: | |
spec: | ||
initContainers: | ||
- name: routing-sidecar | ||
image: ghcr.io/llm-d/llm-d-routing-sidecar:latest | ||
image: ${ROUTING_SIDECAR_IMAGE} | ||
There was a problem hiding this comment. Choose a reason for hiding this commentThe reason will be displayed to describe this comment to others. Learn more. Please undo this change. The file as it was allows the YAML file to be used outside of the kind based tests. |
||
imagePullPolicy: IfNotPresent | ||
args: | ||
- "--port=8000" | ||
|
@@ -61,7 +61,7 @@ spec: | |
restartPolicy: Always | ||
containers: | ||
- name: vllm | ||
image: ghcr.io/llm-d/llm-d-inference-sim:latest | ||
image: ${VLLM_SIMULATOR_IMAGE} | ||
There was a problem hiding this comment. Choose a reason for hiding this commentThe reason will be displayed to describe this comment to others. Learn more. Please undo this change. The file as it was allows the YAML file to be used outside of the kind based tests. |
||
imagePullPolicy: IfNotPresent | ||
args: | ||
- "--port=8200" | ||
|
Original file line number | Diff line number | Diff line change |
---|---|---|
|
@@ -10,9 +10,3 @@ kind: Kustomization | |
|
||
resources: | ||
- deployments.yaml | ||
|
||
images: | ||
- name: ghcr.io/llm-d/llm-d-inference-sim | ||
newTag: ${VLLM_SIMULATOR_TAG} | ||
- name: ghcr.io/llm-d/llm-d-routing-sidecar | ||
newTag: ${ROUTING_SIDECAR_TAG} | ||
There was a problem hiding this comment. Choose a reason for hiding this commentThe reason will be displayed to describe this comment to others. Learn more. Please undo this change. The file as it was allows the YAML file to be used outside of the kind based tests. |
Original file line number | Diff line number | Diff line change |
---|---|---|
|
@@ -16,7 +16,7 @@ spec: | |
spec: | ||
containers: | ||
- name: vllm | ||
image: ghcr.io/llm-d/llm-d-inference-sim:latest | ||
image: ${VLLM_SIMULATOR_IMAGE} | ||
There was a problem hiding this comment. Choose a reason for hiding this commentThe reason will be displayed to describe this comment to others. Learn more. Please undo this change. The file as it was allows the YAML file to be used outside of the kind based tests. |
||
imagePullPolicy: IfNotPresent | ||
args: | ||
- "--port=8000" | ||
|
Original file line number | Diff line number | Diff line change |
---|---|---|
|
@@ -10,7 +10,3 @@ kind: Kustomization | |
|
||
resources: | ||
- deployments.yaml | ||
|
||
images: | ||
- name: ghcr.io/llm-d/llm-d-inference-sim | ||
newTag: ${VLLM_SIMULATOR_TAG} | ||
There was a problem hiding this comment. Choose a reason for hiding this commentThe reason will be displayed to describe this comment to others. Learn more. Please undo this change. The file as it was allows the YAML file to be used outside of the kind based tests. |
Original file line number | Diff line number | Diff line change |
---|---|---|
|
@@ -7,7 +7,7 @@ spec: | |
spec: | ||
containers: | ||
- name: epp | ||
image: ${EPP_IMAGE}:${EPP_TAG} | ||
image: ${EPP_IMAGE} | ||
There was a problem hiding this comment. Choose a reason for hiding this commentThe reason will be displayed to describe this comment to others. Learn more. Please undo this change. The file as it was allows the YAML file to be used outside of the kind based tests. |
||
imagePullPolicy: Always | ||
args: | ||
- --pool-name | ||
|
Original file line number | Diff line number | Diff line change |
---|---|---|
|
@@ -16,5 +16,5 @@ spec: | |
serviceAccountName: operator-controller-manager | ||
containers: | ||
- name: cmd | ||
image: ${IMAGE_TAG_BASE}:${VERSION} | ||
image: ${EPP_IMAGE} | ||
There was a problem hiding this comment. Choose a reason for hiding this commentThe reason will be displayed to describe this comment to others. Learn more. Please undo this change. The file as it was allows the YAML file to be used outside of the kind based tests. |
||
imagePullPolicy: Always |
Original file line number | Diff line number | Diff line change |
---|---|---|
|
@@ -22,12 +22,6 @@ configMapGenerator: | |
disableNameSuffixHash: true | ||
|
||
# Include patches to update the Service, StatefulSet, Route, and RBAC resources. | ||
|
||
# Define the image to be updated. | ||
# images: | ||
# - name: ghcr.io/llm-d/placeholder | ||
# newName: ghcr.io/llm-d/${IMAGE_TAG_BASE} | ||
# newTag: ${VERSION} | ||
There was a problem hiding this comment. Choose a reason for hiding this commentThe reason will be displayed to describe this comment to others. Learn more. Please undo this change. The file as it was allows the YAML file to be used outside of the kind based tests. |
||
patches: | ||
- path: common/patch-service.yaml | ||
- path: common/patch-statefulset.yaml | ||
|
Original file line number | Diff line number | Diff line change |
---|---|---|
|
@@ -23,16 +23,10 @@ SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)" | |
: "${IMAGE_REGISTRY:=ghcr.io/llm-d}" | ||
|
||
# Set a default VLLM_SIMULATOR_IMAGE if not provided | ||
: "${VLLM_SIMULATOR_IMAGE:=llm-d-inference-sim}" | ||
|
||
# Set a default VLLM_SIMULATOR_TAG if not provided | ||
export VLLM_SIMULATOR_TAG="${VLLM_SIMULATOR_TAG:-latest}" | ||
export VLLM_SIMULATOR_IMAGE="${VLLM_SIMULATOR_IMAGE:-ghcr.io/llm-d/llm-d-inference-sim:latest}" | ||
There was a problem hiding this comment. Choose a reason for hiding this commentThe reason will be displayed to describe this comment to others. Learn more. It is very useful to keep the TAG separate from the image name. Please undo this change |
||
|
||
# Set a default EPP_IMAGE if not provided | ||
: "${EPP_IMAGE:=llm-d-inference-scheduler}" | ||
|
||
# Set a default EPP_TAG if not provided | ||
export EPP_TAG="${EPP_TAG:-dev}" | ||
export EPP_IMAGE="${EPP_IMAGE:-ghcr.io/llm-d/llm-d-inference-scheduler:dev}" | ||
There was a problem hiding this comment. Choose a reason for hiding this commentThe reason will be displayed to describe this comment to others. Learn more. It is very useful to keep the TAG separate from the image name. Please undo this change |
||
|
||
# Set the model name to deploy | ||
export MODEL_NAME="${MODEL_NAME:-food-review}" | ||
|
@@ -46,8 +40,8 @@ export MODEL_NAME_SAFE=$(echo "${MODEL_ID}" | tr '[:upper:]' '[:lower:]' | tr ' | |
# Set the endpoint-picker to deploy | ||
export EPP_NAME="${EPP_NAME:-${MODEL_NAME_SAFE}-endpoint-picker}" | ||
|
||
# Set the default routing side car image tag | ||
export ROUTING_SIDECAR_TAG="${ROUTING_SIDECAR_TAG:-0.0.6}" | ||
# Set the default routing side car image | ||
export ROUTING_SIDECAR_IMAGE="${ROUTING_SIDECAR_IMAGE:-ghcr.io/llm-d/llm-d-routing-sidecar:v0.2.0}" | ||
There was a problem hiding this comment. Choose a reason for hiding this commentThe reason will be displayed to describe this comment to others. Learn more. It is very useful to keep the TAG separate from the image name. Please undo this change |
||
|
||
# Set the inference pool name for the deployment | ||
export POOL_NAME="${POOL_NAME:-${MODEL_NAME_SAFE}-inference-pool}" | ||
|
@@ -152,19 +146,19 @@ kubectl --context ${KUBE_CONTEXT} -n local-path-storage wait --for=condition=Rea | |
|
||
# Load the vllm simulator image into the cluster | ||
if [ "${CONTAINER_RUNTIME}" == "podman" ]; then | ||
podman save ${IMAGE_REGISTRY}/${VLLM_SIMULATOR_IMAGE}:${VLLM_SIMULATOR_TAG} -o /dev/stdout | kind --name ${CLUSTER_NAME} load image-archive /dev/stdin | ||
podman save ${VLLM_SIMULATOR_IMAGE} -o /dev/stdout | kind --name ${CLUSTER_NAME} load image-archive /dev/stdin | ||
There was a problem hiding this comment. Choose a reason for hiding this commentThe reason will be displayed to describe this comment to others. Learn more. Please undo this change due to other changes that are requested to be undone. |
||
else | ||
if docker image inspect "${IMAGE_REGISTRY}/${VLLM_SIMULATOR_IMAGE}:${VLLM_SIMULATOR_TAG}" > /dev/null 2>&1; then | ||
if docker image inspect ${VLLM_SIMULATOR_IMAGE} > /dev/null 2>&1; then | ||
echo "INFO: Loading image into KIND cluster..." | ||
There was a problem hiding this comment. Choose a reason for hiding this commentThe reason will be displayed to describe this comment to others. Learn more. Please undo this change due to other changes that are requested to be undone. |
||
kind --name ${CLUSTER_NAME} load docker-image ${IMAGE_REGISTRY}/${VLLM_SIMULATOR_IMAGE}:${VLLM_SIMULATOR_TAG} | ||
kind --name ${CLUSTER_NAME} load docker-image ${VLLM_SIMULATOR_IMAGE} | ||
There was a problem hiding this comment. Choose a reason for hiding this commentThe reason will be displayed to describe this comment to others. Learn more. Please undo this change due to other changes that are requested to be undone. |
||
fi | ||
fi | ||
|
||
# Load the ext_proc endpoint-picker image into the cluster | ||
if [ "${CONTAINER_RUNTIME}" == "podman" ]; then | ||
podman save ${IMAGE_REGISTRY}/${EPP_IMAGE}:${EPP_TAG} -o /dev/stdout | kind --name ${CLUSTER_NAME} load image-archive /dev/stdin | ||
podman save ${EPP_IMAGE} -o /dev/stdout | kind --name ${CLUSTER_NAME} load image-archive /dev/stdin | ||
There was a problem hiding this comment. Choose a reason for hiding this commentThe reason will be displayed to describe this comment to others. Learn more. Please undo this change due to other changes that are requested to be undone. |
||
else | ||
kind --name ${CLUSTER_NAME} load docker-image ${IMAGE_REGISTRY}/${EPP_IMAGE}:${EPP_TAG} | ||
kind --name ${CLUSTER_NAME} load docker-image ${EPP_IMAGE} | ||
There was a problem hiding this comment. Choose a reason for hiding this commentThe reason will be displayed to describe this comment to others. Learn more. Please undo this change due to other changes that are requested to be undone. |
||
fi | ||
# ------------------------------------------------------------------------------ | ||
# CRD Deployment (Gateway API + GIE) | ||
|
@@ -194,8 +188,8 @@ kubectl --context ${KUBE_CONTEXT} delete configmap epp-config --ignore-not-found | |
kubectl --context ${KUBE_CONTEXT} create configmap epp-config --from-file=epp-config.yaml=${EPP_CONFIG} | ||
|
||
kustomize build --enable-helm ${KUSTOMIZE_DIR} \ | ||
| envsubst '${POOL_NAME} ${MODEL_NAME} ${MODEL_NAME_SAFE} ${EPP_NAME} ${EPP_TAG} ${VLLM_SIMULATOR_TAG} \ | ||
${PD_ENABLED} ${KV_CACHE_ENABLED} ${ROUTING_SIDECAR_TAG} \ | ||
| envsubst '${POOL_NAME} ${MODEL_NAME} ${MODEL_NAME_SAFE} ${EPP_NAME} ${EPP_IMAGE} ${VLLM_SIMULATOR_IMAGE} \ | ||
${PD_ENABLED} ${KV_CACHE_ENABLED} ${ROUTING_SIDECAR_IMAGE} \ | ||
There was a problem hiding this comment. Choose a reason for hiding this commentThe reason will be displayed to describe this comment to others. Learn more. Please undo this change due to other changes that are requested to be undone. |
||
${VLLM_REPLICA_COUNT} ${VLLM_REPLICA_COUNT_P} ${VLLM_REPLICA_COUNT_D}' \ | ||
| kubectl --context ${KUBE_CONTEXT} apply -f - | ||
|
||
|
Original file line number | Diff line number | Diff line change |
---|---|---|
|
@@ -31,9 +31,6 @@ if [[ ! -f "$VLLM_CHART_DIR/Chart.yaml" ]]; then | |
exit 1 | ||
fi | ||
|
||
# Default image registry for pulling deployment images | ||
export IMAGE_REGISTRY="${IMAGE_REGISTRY:-ghcr.io/llm-d}" | ||
|
||
There was a problem hiding this comment. Choose a reason for hiding this commentThe reason will be displayed to describe this comment to others. Learn more. Please undo this change due to other changes that are requested to be undone. |
||
# ----------------------------------------------------------------------------- | ||
# Model Configuration | ||
# ----------------------------------------------------------------------------- | ||
|
@@ -72,10 +69,7 @@ export POOL_NAME="${POOL_NAME:-${MODEL_NAME_SAFE}-inference-pool}" | |
export EPP_NAME="${EPP_NAME:-${MODEL_NAME_SAFE}-endpoint-picker}" | ||
|
||
# EPP container image name | ||
export EPP_IMAGE="${EPP_IMAGE:-${IMAGE_REGISTRY}/llm-d-inference-scheduler}" | ||
|
||
# EPP image tag | ||
export EPP_TAG="${EPP_TAG:-v0.1.0}" | ||
export EPP_IMAGE="${EPP_IMAGE:-ghcr.io/llm-d/llm-d-inference-scheduler:dev}" | ||
|
||
# Whether P/D mode is enabled for this deployment | ||
export PD_ENABLED="\"${PD_ENABLED:-false}\"" | ||
|
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Please undo this change. The file as it was allows the YAML file to be used outside of the kind based tests.