biondizzle/vllm
1
0
Fork 0
Code Issues Pull Requests Actions 2 Packages Projects Releases Wiki Activity

Add example of helm chart for vllm deployment on k8s (#9199)

Browse Source 
Signed-off-by: Maxime Fournioux <55544262+mfournioux@users.noreply.github.com>
This commit is contained in:
Maxime Fournioux
2024-12-10 10:19:27 +01:00
committed by GitHub
parent 82c73fd510
commit fe2e10c71b
20 changed files with 1206 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

265
examples/chart-helm/values.schema.json Normal file
View File

@@ -0,0 +1,265 @@
{
"$schema": "http://json-schema.org/schema#",
"type": "object",
"properties": {
"image": {
"type": "object",
"properties": {
"repository": {
"type": "string"
},
"tag": {
"type": "string"
},
"command": {
"type": "array",
"items": {
"type": "string"
}
}
},
"required": [
"command",
"repository",
"tag"
]
},
"containerPort": {
"type": "integer"
},
"serviceName": {
"type": "null"
},
"servicePort": {
"type": "integer"
},
"extraPorts": {
"type": "array"
},
"replicaCount": {
"type": "integer"
},
"deploymentStrategy": {
"type": "object"
},
"resources": {
"type": "object",
"properties": {
"requests": {
"type": "object",
"properties": {
"cpu": {
"type": "integer"
},
"memory": {
"type": "string"
},
"nvidia.com/gpu": {
"type": "integer"
}
},
"required": [
"cpu",
"memory",
"nvidia.com/gpu"
]
},
"limits": {
"type": "object",
"properties": {
"cpu": {
"type": "integer"
},
"memory": {
"type": "string"
},
"nvidia.com/gpu": {
"type": "integer"
}
},
"required": [
"cpu",
"memory",
"nvidia.com/gpu"
]
}
},
"required": [
"limits",
"requests"
]
},
"gpuModels": {
"type": "array",
"items": {
"type": "string"
}
},
"autoscaling": {
"type": "object",
"properties": {
"enabled": {
"type": "boolean"
},
"minReplicas": {
"type": "integer"
},
"maxReplicas": {
"type": "integer"
},
"targetCPUUtilizationPercentage": {
"type": "integer"
}
},
"required": [
"enabled",
"maxReplicas",
"minReplicas",
"targetCPUUtilizationPercentage"
]
},
"configs": {
"type": "object"
},
"secrets": {
"type": "object"
},
"externalConfigs": {
"type": "array"
},
"customObjects": {
"type": "array"
},
"maxUnavailablePodDisruptionBudget": {
"type": "string"
},
"extraInit": {
"type": "object",
"properties": {
"s3modelpath": {
"type": "string"
},
"pvcStorage": {
"type": "string"
},
"awsEc2MetadataDisabled": {
"type": "boolean"
}
},
"required": [
"pvcStorage",
"s3modelpath",
"awsEc2MetadataDisabled"
]
},
"extraContainers": {
"type": "array"
},
"readinessProbe": {
"type": "object",
"properties": {
"initialDelaySeconds": {
"type": "integer"
},
"periodSeconds": {
"type": "integer"
},
"failureThreshold": {
"type": "integer"
},
"httpGet": {
"type": "object",
"properties": {
"path": {
"type": "string"
},
"port": {
"type": "integer"
}
},
"required": [
"path",
"port"
]
}
},
"required": [
"failureThreshold",
"httpGet",
"initialDelaySeconds",
"periodSeconds"
]
},
"livenessProbe": {
"type": "object",
"properties": {
"initialDelaySeconds": {
"type": "integer"
},
"failureThreshold": {
"type": "integer"
},
"periodSeconds": {
"type": "integer"
},
"httpGet": {
"type": "object",
"properties": {
"path": {
"type": "string"
},
"port": {
"type": "integer"
}
},
"required": [
"path",
"port"
]
}
},
"required": [
"failureThreshold",
"httpGet",
"initialDelaySeconds",
"periodSeconds"
]
},
"labels": {
"type": "object",
"properties": {
"environment": {
"type": "string"
},
"release": {
"type": "string"
}
},
"required": [
"environment",
"release"
]
}
},
"required": [
"autoscaling",
"configs",
"containerPort",
"customObjects",
"deploymentStrategy",
"externalConfigs",
"extraContainers",
"extraInit",
"extraPorts",
"gpuModels",
"image",
"labels",
"livenessProbe",
"maxUnavailablePodDisruptionBudget",
"readinessProbe",
"replicaCount",
"resources",
"secrets",
"servicePort"
]
}