Plan a digest-pinned external artifact build - InferCrane

POST

/

api

/

v1

/

optimized-artifacts

Plan a digest-pinned external artifact build

curl --request POST \
  --url http://127.0.0.1:18000/api/v1/optimized-artifacts \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --header 'Idempotency-Key: <idempotency-key>' \
  --data '
{
  "algorithm": "<string>",
  "base_model_artifact_id": "<string>",
  "builder_image_digest": "<string>",
  "configuration": {},
  "format": "<string>",
  "hardware_constraints": {},
  "license_spdx": "<string>",
  "requires_quality_review": true,
  "tool_version": "<string>",
  "calibration_digest": "<string>"
}
'

import requests

url = "http://127.0.0.1:18000/api/v1/optimized-artifacts"

payload = {
    "algorithm": "<string>",
    "base_model_artifact_id": "<string>",
    "builder_image_digest": "<string>",
    "configuration": {},
    "format": "<string>",
    "hardware_constraints": {},
    "license_spdx": "<string>",
    "requires_quality_review": True,
    "tool_version": "<string>",
    "calibration_digest": "<string>"
}
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({
    algorithm: '<string>',
    base_model_artifact_id: '<string>',
    builder_image_digest: '<string>',
    configuration: {},
    format: '<string>',
    hardware_constraints: {},
    license_spdx: '<string>',
    requires_quality_review: true,
    tool_version: '<string>',
    calibration_digest: '<string>'
  })
};

fetch('http://127.0.0.1:18000/api/v1/optimized-artifacts', 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/optimized-artifacts"

	payload := strings.NewReader("{\n  \"algorithm\": \"<string>\",\n  \"base_model_artifact_id\": \"<string>\",\n  \"builder_image_digest\": \"<string>\",\n  \"configuration\": {},\n  \"format\": \"<string>\",\n  \"hardware_constraints\": {},\n  \"license_spdx\": \"<string>\",\n  \"requires_quality_review\": true,\n  \"tool_version\": \"<string>\",\n  \"calibration_digest\": \"<string>\"\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))

}

{}

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

Authorizations

Authorization

string

header

required

Bearer authentication header of the form Bearer <token>, where <token> is your auth token.

Headers

Idempotency-Key

string

required

Stable key used to adopt the original durable operation after retries or disconnects.

Maximum string length: 128

Body

application/json

algorithm

string

required

Minimum string length: 1

base_model_artifact_id

string

required

Minimum string length: 1

builder_image_digest

string

required

Pattern: ^sha256:[a-fA-F0-9]{64}$

configuration

object

required

format

string

required

Minimum string length: 1

hardware_constraints

object

required

kind

enum<string>

required

Available options:

quantized_checkpoint,

speculator_checkpoint,

tensorrt_engine

license_spdx

string

required

Minimum string length: 1

requires_quality_review

boolean

required

tool

enum<string>

required

Available options:

llm-compressor,

modelopt,

vllm-speculators,

tensorrt-llm

tool_version

string

required

Minimum string length: 1

calibration_digest

string

Pattern: ^sha256:[a-fA-F0-9]{64}$

Response

Created

The response is of type object.

⌘I

Plan a digest-pinned external artifact build

curl --request POST \
  --url http://127.0.0.1:18000/api/v1/optimized-artifacts \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --header 'Idempotency-Key: <idempotency-key>' \
  --data '
{
  "algorithm": "<string>",
  "base_model_artifact_id": "<string>",
  "builder_image_digest": "<string>",
  "configuration": {},
  "format": "<string>",
  "hardware_constraints": {},
  "license_spdx": "<string>",
  "requires_quality_review": true,
  "tool_version": "<string>",
  "calibration_digest": "<string>"
}
'

import requests

url = "http://127.0.0.1:18000/api/v1/optimized-artifacts"

payload = {
    "algorithm": "<string>",
    "base_model_artifact_id": "<string>",
    "builder_image_digest": "<string>",
    "configuration": {},
    "format": "<string>",
    "hardware_constraints": {},
    "license_spdx": "<string>",
    "requires_quality_review": True,
    "tool_version": "<string>",
    "calibration_digest": "<string>"
}
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({
    algorithm: '<string>',
    base_model_artifact_id: '<string>',
    builder_image_digest: '<string>',
    configuration: {},
    format: '<string>',
    hardware_constraints: {},
    license_spdx: '<string>',
    requires_quality_review: true,
    tool_version: '<string>',
    calibration_digest: '<string>'
  })
};

fetch('http://127.0.0.1:18000/api/v1/optimized-artifacts', 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/optimized-artifacts"

	payload := strings.NewReader("{\n  \"algorithm\": \"<string>\",\n  \"base_model_artifact_id\": \"<string>\",\n  \"builder_image_digest\": \"<string>\",\n  \"configuration\": {},\n  \"format\": \"<string>\",\n  \"hardware_constraints\": {},\n  \"license_spdx\": \"<string>\",\n  \"requires_quality_review\": true,\n  \"tool_version\": \"<string>\",\n  \"calibration_digest\": \"<string>\"\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))

}

{}

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