Create a CoreWeave inference checkpoint hot-load

Create hot-load

curl --request POST \
  --url https://api.coreweave.com/v1alpha1/inference/hotLoads \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "deploymentId": "<string>",
  "identity": "<string>",
  "hotLoadId": "<string>"
}
'

import requests

url = "https://api.coreweave.com/v1alpha1/inference/hotLoads"

payload = {
    "deploymentId": "<string>",
    "identity": "<string>",
    "hotLoadId": "<string>"
}
headers = {
    "Authorization": "Bearer <token>",
    "Content-Type": "application/json"
}

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

print(response.text)

const options = {
  method: 'POST',
  headers: {Authorization: 'Bearer <token>', 'Content-Type': 'application/json'},
  body: JSON.stringify({deploymentId: '<string>', identity: '<string>', hotLoadId: '<string>'})
};

fetch('https://api.coreweave.com/v1alpha1/inference/hotLoads', options)
  .then(res => res.json())
  .then(res => console.log(res))
  .catch(err => console.error(err));

<?php

$curl = curl_init();

curl_setopt_array($curl, [
  CURLOPT_URL => "https://api.coreweave.com/v1alpha1/inference/hotLoads",
  CURLOPT_RETURNTRANSFER => true,
  CURLOPT_ENCODING => "",
  CURLOPT_MAXREDIRS => 10,
  CURLOPT_TIMEOUT => 30,
  CURLOPT_HTTP_VERSION => CURL_HTTP_VERSION_1_1,
  CURLOPT_CUSTOMREQUEST => "POST",
  CURLOPT_POSTFIELDS => json_encode([
    'deploymentId' => '<string>',
    'identity' => '<string>',
    'hotLoadId' => '<string>'
  ]),
  CURLOPT_HTTPHEADER => [
    "Authorization: Bearer <token>",
    "Content-Type: application/json"
  ],
]);

$response = curl_exec($curl);
$err = curl_error($curl);

curl_close($curl);

if ($err) {
  echo "cURL Error #:" . $err;
} else {
  echo $response;
}

package main

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

func main() {

	url := "https://api.coreweave.com/v1alpha1/inference/hotLoads"

	payload := strings.NewReader("{\n  \"deploymentId\": \"<string>\",\n  \"identity\": \"<string>\",\n  \"hotLoadId\": \"<string>\"\n}")

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

	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))

}

HttpResponse<String> response = Unirest.post("https://api.coreweave.com/v1alpha1/inference/hotLoads")
  .header("Authorization", "Bearer <token>")
  .header("Content-Type", "application/json")
  .body("{\n  \"deploymentId\": \"<string>\",\n  \"identity\": \"<string>\",\n  \"hotLoadId\": \"<string>\"\n}")
  .asString();

require 'uri'
require 'net/http'

url = URI("https://api.coreweave.com/v1alpha1/inference/hotLoads")

http = Net::HTTP.new(url.host, url.port)
http.use_ssl = true

request = Net::HTTP::Post.new(url)
request["Authorization"] = 'Bearer <token>'
request["Content-Type"] = 'application/json'
request.body = "{\n  \"deploymentId\": \"<string>\",\n  \"identity\": \"<string>\",\n  \"hotLoadId\": \"<string>\"\n}"

response = http.request(request)
puts response.read_body

{
  "hotLoad": {
    "spec": {
      "id": "<string>",
      "deploymentId": "<string>",
      "organizationId": "<string>",
      "identity": "<string>",
      "type": "SNAPSHOT_TYPE_UNSPECIFIED",
      "incrementalSnapshotMetadata": {
        "previousSnapshotIdentity": "<string>",
        "compressionFormat": "COMPRESSION_FORMAT_ZSTD",
        "checksumFormat": "CHECKSUM_FORMAT_ADLER32"
      },
      "promptCachePolicy": "PROMPT_CACHE_POLICY_UNSPECIFIED",
      "snapshotChain": [
        {
          "identity": "<string>",
          "type": "SNAPSHOT_TYPE_UNSPECIFIED",
          "compressionFormat": "COMPRESSION_FORMAT_UNSPECIFIED",
          "checksumFormat": "CHECKSUM_FORMAT_UNSPECIFIED",
          "hotLoadId": "<string>"
        }
      ]
    },
    "status": {
      "createdAt": "2023-11-07T05:31:56Z",
      "updatedAt": "2023-11-07T05:31:56Z",
      "finishedAt": "2023-11-07T05:31:56Z",
      "state": "HOT_LOAD_STATE_UNSPECIFIED",
      "conditions": [
        {
          "type": "<string>",
          "status": "STATUS_UNSPECIFIED",
          "lastUpdateTime": "2023-11-07T05:31:56Z",
          "reason": "<string>",
          "message": "<string>",
          "zone": "<string>"
        }
      ],
      "canceledAt": "2023-11-07T05:31:56Z"
    }
  }
}

{
  "code": 123,
  "message": "<string>",
  "details": [
    {
      "@type": "<string>"
    }
  ]
}

POST

v1alpha1

inference

hotLoads

Create hot-load

curl --request POST \
  --url https://api.coreweave.com/v1alpha1/inference/hotLoads \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "deploymentId": "<string>",
  "identity": "<string>",
  "hotLoadId": "<string>"
}
'

import requests

url = "https://api.coreweave.com/v1alpha1/inference/hotLoads"

payload = {
    "deploymentId": "<string>",
    "identity": "<string>",
    "hotLoadId": "<string>"
}
headers = {
    "Authorization": "Bearer <token>",
    "Content-Type": "application/json"
}

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

print(response.text)

const options = {
  method: 'POST',
  headers: {Authorization: 'Bearer <token>', 'Content-Type': 'application/json'},
  body: JSON.stringify({deploymentId: '<string>', identity: '<string>', hotLoadId: '<string>'})
};

fetch('https://api.coreweave.com/v1alpha1/inference/hotLoads', options)
  .then(res => res.json())
  .then(res => console.log(res))
  .catch(err => console.error(err));

<?php

$curl = curl_init();

curl_setopt_array($curl, [
  CURLOPT_URL => "https://api.coreweave.com/v1alpha1/inference/hotLoads",
  CURLOPT_RETURNTRANSFER => true,
  CURLOPT_ENCODING => "",
  CURLOPT_MAXREDIRS => 10,
  CURLOPT_TIMEOUT => 30,
  CURLOPT_HTTP_VERSION => CURL_HTTP_VERSION_1_1,
  CURLOPT_CUSTOMREQUEST => "POST",
  CURLOPT_POSTFIELDS => json_encode([
    'deploymentId' => '<string>',
    'identity' => '<string>',
    'hotLoadId' => '<string>'
  ]),
  CURLOPT_HTTPHEADER => [
    "Authorization: Bearer <token>",
    "Content-Type: application/json"
  ],
]);

$response = curl_exec($curl);
$err = curl_error($curl);

curl_close($curl);

if ($err) {
  echo "cURL Error #:" . $err;
} else {
  echo $response;
}

package main

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

func main() {

	url := "https://api.coreweave.com/v1alpha1/inference/hotLoads"

	payload := strings.NewReader("{\n  \"deploymentId\": \"<string>\",\n  \"identity\": \"<string>\",\n  \"hotLoadId\": \"<string>\"\n}")

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

	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))

}

HttpResponse<String> response = Unirest.post("https://api.coreweave.com/v1alpha1/inference/hotLoads")
  .header("Authorization", "Bearer <token>")
  .header("Content-Type", "application/json")
  .body("{\n  \"deploymentId\": \"<string>\",\n  \"identity\": \"<string>\",\n  \"hotLoadId\": \"<string>\"\n}")
  .asString();

require 'uri'
require 'net/http'

url = URI("https://api.coreweave.com/v1alpha1/inference/hotLoads")

http = Net::HTTP.new(url.host, url.port)
http.use_ssl = true

request = Net::HTTP::Post.new(url)
request["Authorization"] = 'Bearer <token>'
request["Content-Type"] = 'application/json'
request.body = "{\n  \"deploymentId\": \"<string>\",\n  \"identity\": \"<string>\",\n  \"hotLoadId\": \"<string>\"\n}"

response = http.request(request)
puts response.read_body

{
  "hotLoad": {
    "spec": {
      "id": "<string>",
      "deploymentId": "<string>",
      "organizationId": "<string>",
      "identity": "<string>",
      "type": "SNAPSHOT_TYPE_UNSPECIFIED",
      "incrementalSnapshotMetadata": {
        "previousSnapshotIdentity": "<string>",
        "compressionFormat": "COMPRESSION_FORMAT_ZSTD",
        "checksumFormat": "CHECKSUM_FORMAT_ADLER32"
      },
      "promptCachePolicy": "PROMPT_CACHE_POLICY_UNSPECIFIED",
      "snapshotChain": [
        {
          "identity": "<string>",
          "type": "SNAPSHOT_TYPE_UNSPECIFIED",
          "compressionFormat": "COMPRESSION_FORMAT_UNSPECIFIED",
          "checksumFormat": "CHECKSUM_FORMAT_UNSPECIFIED",
          "hotLoadId": "<string>"
        }
      ]
    },
    "status": {
      "createdAt": "2023-11-07T05:31:56Z",
      "updatedAt": "2023-11-07T05:31:56Z",
      "finishedAt": "2023-11-07T05:31:56Z",
      "state": "HOT_LOAD_STATE_UNSPECIFIED",
      "conditions": [
        {
          "type": "<string>",
          "status": "STATUS_UNSPECIFIED",
          "lastUpdateTime": "2023-11-07T05:31:56Z",
          "reason": "<string>",
          "message": "<string>",
          "zone": "<string>"
        }
      ],
      "canceledAt": "2023-11-07T05:31:56Z"
    }
  }
}

{
  "code": 123,
  "message": "<string>",
  "details": [
    {
      "@type": "<string>"
    }
  ]
}

The API server is https://api.coreweave.com.
Replace {API_ACCESS_TOKEN} with your CoreWeave API access token.
For required permissions, see IAM Access Policies.

The target checkpoint is named by identity, a single path segment beneath the deployment’s configured bucket and path prefix. The bucket and prefix come from the deployment, so this request carries no storage location. A deployment runs one hot-load at a time. Creating a second while one is unfinished fails, and the same interlock blocks deployment updates while a hot-load is running. Delta checkpoints require incrementalSnapshotMetadata, and their resolved chain holds at most 128 deltas before a full checkpoint is needed to reset it.

Example request

curl -X POST https://api.coreweave.com/v1alpha1/inference/hotLoads \
       -H "Content-Type: application/json" \
       -H "Authorization: Bearer {API_ACCESS_TOKEN}" \
       -d @data.json

Autorisations

Authorization

string

header

défaut:Bearer {API_ACCESS_TOKEN}

requis

CoreWeave API access token sent as a bearer token.

Corps

application/json

Request for CreateHotLoad

deploymentId

string

requis

The ID of the deployment to hot-load

identity

string

requis

The identity of the target snapshot within the deployment. Must be a single path segment. Multiple hot-load operations may target the same snapshot identity.

type

enum<string>

requis

The type of the target snapshot. SNAPSHOT_TYPE_FULL carries a complete set of model weights and starts a new snapshot chain. SNAPSHOT_TYPE_INCREMENTAL is a delta against an earlier snapshot and requires incrementalSnapshotMetadata. This field is required; the zero value is rejected.

Options disponibles:

SNAPSHOT_TYPE_FULL,

SNAPSHOT_TYPE_INCREMENTAL

hotLoadId

string

The ID to use for the hot-load, which becomes its permanent identifier. Must be a UUID. If omitted, one is generated. Creating a second hot-load with an ID that already exists in the caller's organization fails with ALREADY_EXISTS; an ID that is unavailable for any other reason fails with INVALID_ARGUMENT.

incrementalSnapshotMetadata

object

Delta metadata, required when type is SNAPSHOT_TYPE_INCREMENTAL

Show child attributes

promptCachePolicy

enum<string>

How the prompt cache is handled once the swap completes. PROMPT_CACHE_POLICY_RESET_ALL prevents reuse of any entry computed before the swap. PROMPT_CACHE_POLICY_PRESERVE allows reuse, knowingly stale under the new weights. The policy applies to requests admitted after the transition, not to requests already in flight. Omit the field rather than sending the zero value; omitting it applies PROMPT_CACHE_POLICY_PRESERVE.

Options disponibles:

PROMPT_CACHE_POLICY_RESET_ALL,

PROMPT_CACHE_POLICY_PRESERVE

Réponse

Response for CreateHotLoad

hotLoad

object

The created hot-load

Show child attributes

Dernière modification le 1 octobre 2026