Skip to content

Move routing-sidecar from an initContainer to a regular container #656

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

Closed
roytman wants to merge 3 commits into from
Closed

Move routing-sidecar from an initContainer to a regular container #656

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
0e7e63a
move routing-sidecar from initContainer to a regular container
roytman Feb 26, 2026
c33eee4
remove restartPolicy from routing-proxy
roytman Feb 27, 2026
6f10948
Merge branch 'main' into initContainer
roytman Feb 27, 2026
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
3 changes: 1 addition & 2 deletions deploy/components/vllm-sim-pd/deployments.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -69,7 +69,7 @@ spec:
app: ${POOL_NAME}
llm-d.ai/role: decode
spec:
initContainers:
containers:
- name: routing-sidecar
image: ${SIDECAR_IMAGE}
imagePullPolicy: IfNotPresent
Expand Down Expand Up @@ -110,7 +110,6 @@ spec:
valueFrom:
fieldRef:
fieldPath: status.podIP
containers:
- name: vllm
image: ${VLLM_SIMULATOR_IMAGE}
imagePullPolicy: IfNotPresent
Expand Down
3 changes: 1 addition & 2 deletions deploy/components/vllm-sim/deployments.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -14,7 +14,7 @@ spec:
labels:
app: ${POOL_NAME}
spec:
initContainers:
containers:
- name: routing-sidecar
image: ${SIDECAR_IMAGE}
imagePullPolicy: IfNotPresent
Expand Down Expand Up @@ -55,7 +55,6 @@ spec:
valueFrom:
fieldRef:
fieldPath: status.podIP
containers:
- name: vllm
image: ${VLLM_SIMULATOR_IMAGE}
imagePullPolicy: IfNotPresent
Expand Down
3 changes: 1 addition & 2 deletions test/e2e/yaml/vllm-sim-dp.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -15,7 +15,7 @@ spec:
app: ${POOL_NAME}
llm-d.ai/role: decode
spec:
initContainers:
containers:
- name: routing-sidecar
image: ${SIDECAR_IMAGE}
imagePullPolicy: IfNotPresent
Expand All @@ -39,7 +39,6 @@ spec:
valueFrom:
fieldRef:
fieldPath: status.podIP
containers:
- name: vllm
image: ${VLLM_SIMULATOR_IMAGE}
imagePullPolicy: IfNotPresent
Expand Down
3 changes: 1 addition & 2 deletions test/e2e/yaml/vllm-sim-pd.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -58,7 +58,7 @@ spec:
app: ${POOL_NAME}
llm-d.ai/role: decode
spec:
initContainers:
containers:
- name: routing-sidecar
image: ${SIDECAR_IMAGE}
imagePullPolicy: IfNotPresent
Expand All @@ -72,7 +72,6 @@ spec:
- containerPort: 8000
protocol: TCP
restartPolicy: Always
containers:
- name: vllm
image: ${VLLM_SIMULATOR_IMAGE}
imagePullPolicy: IfNotPresent
Expand Down
4 changes: 1 addition & 3 deletions test/sidecar/config/base/pod-qwen.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -3,13 +3,12 @@ kind: Pod
metadata:
name: qwen2-0--5b
spec:
initContainers:
containers:
- name: routing-proxy
image: routing-proxy
args:
- "--port=8000"
- "--vllm-port=8001"
restartPolicy: Always
# readinessProbe:
# exec:
# command:
Expand All @@ -22,7 +21,6 @@ spec:
# - "true"
# initialDelaySeconds: 1
# periodSeconds: 360
containers:
- name: vllm
image: vllm/vllm-openai:v0.8.2
args:
Expand Down
4 changes: 1 addition & 3 deletions test/sidecar/config/nixl/qwen-decoder-pod.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -17,7 +17,7 @@ spec:
operator: In
values:
- NVIDIA-A100-SXM4-80GB
initContainers:
containers:
- name: routing-proxy
image: routing-proxy
securityContext:
Expand All @@ -31,9 +31,7 @@ spec:
ports:
- containerPort: 8000
protocol: TCP
restartPolicy: Always
imagePullPolicy: Always
containers:
- name: vllm
image: vllm-openai
securityContext:
Expand Down