File tree Expand file tree Collapse file tree 2 files changed +7
-3
lines changed Expand file tree Collapse file tree 2 files changed +7
-3
lines changed Original file line number Diff line number Diff line change 1515apiVersion : nvidia.com/v1alpha1
1616kind : DynamoGraphDeployment
1717metadata :
18- name : vllm-v1-agg
18+ name : vllm-v1-agg-router
1919spec :
2020 services :
2121 Frontend :
3737 periodSeconds : 60
3838 timeoutSeconds : 30
3939 failureThreshold : 10
40- dynamoNamespace : vllm-v1-agg
40+ dynamoNamespace : vllm-v1-agg-router
4141 componentType : main
4242 replicas : 1
4343 resources :
5858 - out=dyn
5959 - --http-port
6060 - " 8000"
61+ - --router-mode
62+ - kv
6163 VllmDecodeWorker :
6264 envFromSecret : hf-token-secret
6365 livenessProbe :
7981 periodSeconds : 60
8082 timeoutSeconds : 30
8183 failureThreshold : 10
82- dynamoNamespace : vllm-v1-agg
84+ dynamoNamespace : vllm-v1-agg-router
8385 componentType : worker
8486 replicas : 2
8587 resources :
Original file line number Diff line number Diff line change 5858 - out=dyn
5959 - --http-port
6060 - " 8000"
61+ - --router-mode
62+ - kv
6163 VllmDecodeWorker :
6264 dynamoNamespace : vllm-v1-disagg-router
6365 envFromSecret : hf-token-secret
You can’t perform that action at this time.
0 commit comments