Create a provider-managed deployment

curl --request POST \
  --url http://127.0.0.1:18000/api/v1/deployments \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --header 'Idempotency-Key: <idempotency-key>' \
  --data '
{
  "cloud": "<string>",
  "gpu": "<string>",
  "model": "<string>",
  "name": "<string>",
  "billing_mode": "provider_account",
  "endpoint_name": "<string>",
  "gpu_count": 1,
  "managed_runtime_seconds": 43650,
  "max_replicas": 1,
  "min_replicas": 1,
  "model_revision": "<string>",
  "model_secret_reference_id": "<string>",
  "port": 32768,
  "provider_adapter": "<string>",
  "region": "<string>",
  "runtime": "vllm",
  "runtime_args": [
    "<string>"
  ],
  "runtime_version": "<string>",
  "serving": {
    "autoscaling": {
      "max": 5000,
      "min": 5000
    },
    "backend": "dynamo",
    "cache": {
      "configuration_ref": "<string>",
      "disk_gib": 1,
      "host_gib": 1,
      "memory_gib": 1,
      "metrics": true,
      "storage_claim": "<string>"
    },
    "decode": {
      "replicas": 5000,
      "tensor_parallelism": 512
    },
    "prefill": {
      "replicas": 5000,
      "tensor_parallelism": 512
    },
    "schema_version": "infercrane.serving/v1",
    "worker": {
      "replicas": 5000,
      "tensor_parallelism": 512
    }
  }
}
'

import requests

url = "http://127.0.0.1:18000/api/v1/deployments"

payload = {
    "cloud": "<string>",
    "gpu": "<string>",
    "model": "<string>",
    "name": "<string>",
    "billing_mode": "provider_account",
    "endpoint_name": "<string>",
    "gpu_count": 1,
    "managed_runtime_seconds": 43650,
    "max_replicas": 1,
    "min_replicas": 1,
    "model_revision": "<string>",
    "model_secret_reference_id": "<string>",
    "port": 32768,
    "provider_adapter": "<string>",
    "region": "<string>",
    "runtime": "vllm",
    "runtime_args": ["<string>"],
    "runtime_version": "<string>",
    "serving": {
        "autoscaling": {
            "max": 5000,
            "min": 5000
        },
        "backend": "dynamo",
        "cache": {
            "configuration_ref": "<string>",
            "disk_gib": 1,
            "host_gib": 1,
            "memory_gib": 1,
            "metrics": True,
            "storage_claim": "<string>"
        },
        "decode": {
            "replicas": 5000,
            "tensor_parallelism": 512
        },
        "prefill": {
            "replicas": 5000,
            "tensor_parallelism": 512
        },
        "schema_version": "infercrane.serving/v1",
        "worker": {
            "replicas": 5000,
            "tensor_parallelism": 512
        }
    }
}
headers = {
    "Idempotency-Key": "<idempotency-key>",
    "Authorization": "Bearer <token>",
    "Content-Type": "application/json"
}

response = requests.post(url, json=payload, headers=headers)

print(response.text)

const options = {
  method: 'POST',
  headers: {
    'Idempotency-Key': '<idempotency-key>',
    Authorization: 'Bearer <token>',
    'Content-Type': 'application/json'
  },
  body: JSON.stringify({
    cloud: '<string>',
    gpu: '<string>',
    model: '<string>',
    name: '<string>',
    billing_mode: 'provider_account',
    endpoint_name: '<string>',
    gpu_count: 1,
    managed_runtime_seconds: 43650,
    max_replicas: 1,
    min_replicas: 1,
    model_revision: '<string>',
    model_secret_reference_id: '<string>',
    port: 32768,
    provider_adapter: '<string>',
    region: '<string>',
    runtime: 'vllm',
    runtime_args: ['<string>'],
    runtime_version: '<string>',
    serving: {
      autoscaling: {max: 5000, min: 5000},
      backend: 'dynamo',
      cache: {
        configuration_ref: '<string>',
        disk_gib: 1,
        host_gib: 1,
        memory_gib: 1,
        metrics: true,
        storage_claim: '<string>'
      },
      decode: {replicas: 5000, tensor_parallelism: 512},
      prefill: {replicas: 5000, tensor_parallelism: 512},
      schema_version: 'infercrane.serving/v1',
      worker: {replicas: 5000, tensor_parallelism: 512}
    }
  })
};

fetch('http://127.0.0.1:18000/api/v1/deployments', options)
  .then(res => res.json())
  .then(res => console.log(res))
  .catch(err => console.error(err));

package main

import (
	"fmt"
	"strings"
	"net/http"
	"io"
)

func main() {

	url := "http://127.0.0.1:18000/api/v1/deployments"

	payload := strings.NewReader("{\n  \"cloud\": \"<string>\",\n  \"gpu\": \"<string>\",\n  \"model\": \"<string>\",\n  \"name\": \"<string>\",\n  \"billing_mode\": \"provider_account\",\n  \"endpoint_name\": \"<string>\",\n  \"gpu_count\": 1,\n  \"managed_runtime_seconds\": 43650,\n  \"max_replicas\": 1,\n  \"min_replicas\": 1,\n  \"model_revision\": \"<string>\",\n  \"model_secret_reference_id\": \"<string>\",\n  \"port\": 32768,\n  \"provider_adapter\": \"<string>\",\n  \"region\": \"<string>\",\n  \"runtime\": \"vllm\",\n  \"runtime_args\": [\n    \"<string>\"\n  ],\n  \"runtime_version\": \"<string>\",\n  \"serving\": {\n    \"autoscaling\": {\n      \"max\": 5000,\n      \"min\": 5000\n    },\n    \"backend\": \"dynamo\",\n    \"cache\": {\n      \"configuration_ref\": \"<string>\",\n      \"disk_gib\": 1,\n      \"host_gib\": 1,\n      \"memory_gib\": 1,\n      \"metrics\": true,\n      \"storage_claim\": \"<string>\"\n    },\n    \"decode\": {\n      \"replicas\": 5000,\n      \"tensor_parallelism\": 512\n    },\n    \"prefill\": {\n      \"replicas\": 5000,\n      \"tensor_parallelism\": 512\n    },\n    \"schema_version\": \"infercrane.serving/v1\",\n    \"worker\": {\n      \"replicas\": 5000,\n      \"tensor_parallelism\": 512\n    }\n  }\n}")

	req, _ := http.NewRequest("POST", url, payload)

	req.Header.Add("Idempotency-Key", "<idempotency-key>")
	req.Header.Add("Authorization", "Bearer <token>")
	req.Header.Add("Content-Type", "application/json")

	res, _ := http.DefaultClient.Do(req)

	defer res.Body.Close()
	body, _ := io.ReadAll(res.Body)

	fmt.Println(string(body))

}

{
  "operation": {
    "id": "<string>",
    "kind": "<string>",
    "progress": 50,
    "status": "pending",
    "attempt": 123,
    "cancel_requested": true,
    "created_at": "2023-11-07T05:31:56Z",
    "current_step": "<string>",
    "current_step_status": "pending",
    "error_code": "<string>",
    "max_attempts": 123,
    "message": "<string>",
    "resource_name": "<string>",
    "resource_type": "<string>",
    "result": {},
    "retryable": true,
    "updated_at": "2023-11-07T05:31:56Z"
  },
  "created": true,
  "deployment": {
    "model": "<string>",
    "name": "<string>",
    "runtime": "<string>",
    "active_revision_id": "<string>",
    "candidate_revision_id": "<string>",
    "endpoint_names": [
      "<string>"
    ],
    "id": "<string>",
    "max_replicas": 123,
    "min_replicas": 123,
    "observed_state": "<string>"
  }
}

{
  "error": {
    "code": "<string>",
    "message": "<string>",
    "category": "<string>",
    "remediation": "<string>",
    "request_id": "<string>",
    "retryable": true
  }
}