How to Deploy VLLM Serverless using Programming Language
Hello how can we achieve deploying Severless
VLLM instances using an API rather than going to the UI?
VLLM instances using an API rather than going to the UI?
YYou can try our graphql api, here is an example:
url: https://api.runpod.io/graphql?api_key=api_key_here
mutation saveEndpoint($input: EndpointInput!) {
saveEndpoint(input: $input) {
gpuIds
id
idleTimeout
locations
name
networkVolumeId
scalerType
scalerValue
templateId
userId
workersMax
workersMin
gpuCount
}
}
// input
{
"gpuIds": "AMPERE_16",
"gpuCount": 1,
"allowedCudaVersions": "",
"idleTimeout": 5,
"locations": null,
"name": "broken_violet_tarantula -fb",
"networkVolumeId": null,
"scalerType": "QUEUE_DELAY",
"scalerValue": 4,
"workersMax": 3,
"workersMin": 0,
"executionTimeoutMs": 600000,
"template": {
"containerDiskInGb": 5,
"containerRegistryAuthId": "",
"dockerArgs": "",
"env": [],
"imageName": "test/test",
"startScript": "",
"ports": "",
"name": "broken_violet_tarantula__template__6oknzg"
}
}url: https://api.runpod.io/graphql?api_key=api_key_here
mutation saveEndpoint($input: EndpointInput!) {
saveEndpoint(input: $input) {
gpuIds
id
idleTimeout
locations
name
networkVolumeId
scalerType
scalerValue
templateId
userId
workersMax
workersMin
gpuCount
}
}
// input
{
"gpuIds": "AMPERE_16",
"gpuCount": 1,
"allowedCudaVersions": "",
"idleTimeout": 5,
"locations": null,
"name": "broken_violet_tarantula -fb",
"networkVolumeId": null,
"scalerType": "QUEUE_DELAY",
"scalerValue": 4,
"workersMax": 3,
"workersMin": 0,
"executionTimeoutMs": 600000,
"template": {
"containerDiskInGb": 5,
"containerRegistryAuthId": "",
"dockerArgs": "",
"env": [],
"imageName": "test/test",
"startScript": "",
"ports": "",
"name": "broken_violet_tarantula__template__6oknzg"
}
}