79 lines
2.5 KiB
JSON
79 lines
2.5 KiB
JSON
{
|
|
"family": "Dynamo-frontend",
|
|
"containerDefinitions": [
|
|
{
|
|
"name": "dynamo-vllm-frontend",
|
|
"image": "nvcr.io/nvidia/ai-dynamo/vllm-runtime:my-tag",
|
|
"repositoryCredentials": {
|
|
"credentialsParameter": "arn:aws:secretsmanager:AWS_REGION:AWS_ID:secret:ngc_nvcr_access"
|
|
},
|
|
"cpu": 0,
|
|
"portMappings": [
|
|
{
|
|
"name": "8000",
|
|
"containerPort": 8000,
|
|
"hostPort": 8000,
|
|
"protocol": "tcp",
|
|
"appProtocol": "http"
|
|
}
|
|
],
|
|
"essential": true,
|
|
"entryPoint": [
|
|
"sh",
|
|
"-c"
|
|
],
|
|
"command": [
|
|
"cd examples/backends/vllm && python -m dynamo.frontend --router-mode kv & python3 -m dynamo.vllm --model Qwen/Qwen3-0.6B --enforce-eager"
|
|
],
|
|
"environment": [
|
|
{
|
|
"name": "ETCD_ENDPOINTS",
|
|
"value": "http://IP_ADDRESS:2379"
|
|
},
|
|
{
|
|
"name": "NATS_SERVER",
|
|
"value": "nats://IP_ADDRESS:4222"
|
|
}
|
|
],
|
|
"environmentFiles": [],
|
|
"mountPoints": [],
|
|
"volumesFrom": [],
|
|
"ulimits": [],
|
|
"logConfiguration": {
|
|
"logDriver": "awslogs",
|
|
"options": {
|
|
"awslogs-group": "/ecs/Dynamo-frontend",
|
|
"mode": "non-blocking",
|
|
"awslogs-create-group": "true",
|
|
"max-buffer-size": "25m",
|
|
"awslogs-region": "AWS_REGION",
|
|
"awslogs-stream-prefix": "ecs"
|
|
},
|
|
"secretOptions": []
|
|
},
|
|
"systemControls": [],
|
|
"resourceRequirements": [
|
|
{
|
|
"value": "1",
|
|
"type": "GPU"
|
|
}
|
|
]
|
|
}
|
|
],
|
|
"taskRoleArn": "arn:aws:iam::AWS_ID:role/ecsTaskExecutionRole",
|
|
"executionRoleArn": "arn:aws:iam::AWS_ID:role/ecsTaskExecutionRole",
|
|
"networkMode": "host",
|
|
"volumes": [],
|
|
"placementConstraints": [],
|
|
"requiresCompatibilities": [
|
|
"EC2"
|
|
],
|
|
"cpu": "2048",
|
|
"memory": "40960",
|
|
"runtimePlatform": {
|
|
"cpuArchitecture": "X86_64",
|
|
"operatingSystemFamily": "LINUX"
|
|
},
|
|
"enableFaultInjection": false
|
|
}
|