Unverified Commit b7667c48 authored by Julien Mancuso's avatar Julien Mancuso Committed by GitHub
Browse files

fix: fix PVC in shared frontend example (#4517)


Signed-off-by: default avatarJulien Mancuso <jmancuso@nvidia.com>
parent b6f31b41
...@@ -19,7 +19,7 @@ spec: ...@@ -19,7 +19,7 @@ spec:
services: services:
Frontend: Frontend:
componentType: frontend componentType: frontend
dynamoNamespace: dynamo globalDynamoNamespace: true
replicas: 1 replicas: 1
extraPodSpec: extraPodSpec:
mainContainer: mainContainer:
...@@ -30,14 +30,15 @@ kind: DynamoGraphDeployment ...@@ -30,14 +30,15 @@ kind: DynamoGraphDeployment
metadata: metadata:
name: vllm-agg name: vllm-agg
spec: spec:
pvcs:
- name: dynamo-model-cache
create: false
services: services:
VllmDecodeWorker: VllmDecodeWorker:
pvc: volumeMounts:
create: false - name: dynamo-model-cache
name: dynamo-model-cache
mountPoint: /root/.cache/huggingface mountPoint: /root/.cache/huggingface
envFromSecret: hf-token-secret envFromSecret: hf-token-secret
dynamoNamespace: vllm-agg
componentType: worker componentType: worker
replicas: 1 replicas: 1
resources: resources:
...@@ -61,12 +62,10 @@ spec: ...@@ -61,12 +62,10 @@ spec:
backendFramework: vllm backendFramework: vllm
services: services:
EncodeWorker: EncodeWorker:
pvc: volumeMounts:
create: false - name: dynamo-model-cache
name: dynamo-model-cache
mountPoint: /root/.cache/huggingface mountPoint: /root/.cache/huggingface
envFromSecret: hf-token-secret envFromSecret: hf-token-secret
dynamoNamespace: agg-qwen
componentType: worker componentType: worker
replicas: 1 replicas: 1
resources: resources:
...@@ -82,12 +81,10 @@ spec: ...@@ -82,12 +81,10 @@ spec:
args: args:
- python3 components/encode_worker.py --model Qwen/Qwen2.5-VL-7B-Instruct - python3 components/encode_worker.py --model Qwen/Qwen2.5-VL-7B-Instruct
VLMWorker: VLMWorker:
pvc: volumeMounts:
create: false - name: dynamo-model-cache
name: dynamo-model-cache
mountPoint: /root/.cache/huggingface mountPoint: /root/.cache/huggingface
envFromSecret: hf-token-secret envFromSecret: hf-token-secret
dynamoNamespace: agg-qwen
componentType: worker componentType: worker
replicas: 1 replicas: 1
resources: resources:
...@@ -103,12 +100,10 @@ spec: ...@@ -103,12 +100,10 @@ spec:
args: args:
- python3 components/worker.py --model Qwen/Qwen2.5-VL-7B-Instruct --worker-type prefill - python3 components/worker.py --model Qwen/Qwen2.5-VL-7B-Instruct --worker-type prefill
Processor: Processor:
pvc: volumeMounts:
create: false - name: dynamo-model-cache
name: dynamo-model-cache
mountPoint: /root/.cache/huggingface mountPoint: /root/.cache/huggingface
envFromSecret: hf-token-secret envFromSecret: hf-token-secret
dynamoNamespace: agg-qwen
componentType: worker componentType: worker
replicas: 1 replicas: 1
resources: resources:
......
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment