dedicated_inference_accelerators

Creates, updates, deletes, gets or lists a dedicated_inference_accelerators resource.

Overview

Name	dedicated_inference_accelerators
Type	Resource
Id	digitalocean.inference.dedicated_inference_accelerators

Fields

The following fields are returned by SELECT queries:

dedicated_inferences_get_accelerator

Single accelerator object.

Name	Datatype	Description
id	string (uuid)	Unique ID of the accelerator. (example: 5b5c619c-359c-44ca-87e2-47e98170c02f)
name	string	Name of the accelerator. (example: mi300x1-ghfpsf)
created_at	string (date-time)	(example: 2024-01-09T20:44:32Z)
role	string	Role of the accelerator (e.g. prefill_decode). (example: prefill_decode)
slug	string	DigitalOcean GPU slug. (example: gpu-mi300x1-192gb)
status	string	Status of the accelerator. (example: active)

dedicated_inferences_list_accelerators

The response will be a JSON object with a key called accelerators. This will be set to an array of accelerator objects. Pagination uses the same links and meta structure as other list endpoints.

Name	Datatype	Description
id	string (uuid)	Unique ID of the accelerator. (example: 5b5c619c-359c-44ca-87e2-47e98170c02f)
name	string	Name of the accelerator. (example: mi300x1-ghfpsf)
created_at	string (date-time)	(example: 2024-01-09T20:44:32Z)
role	string	Role of the accelerator (e.g. prefill_decode). (example: prefill_decode)
slug	string	DigitalOcean GPU slug. (example: gpu-mi300x1-192gb)
status	string	Status of the accelerator. (example: active)

Methods

The following methods are available for this resource:

Name	Accessible by	Required Params	Optional Params	Description
dedicated_inferences_get_accelerator	select	dedicated_inference_id, accelerator_id		Retrieve a single accelerator by ID for a Dedicated Inference instance. Send a GET request to /v2/dedicated-inferences/{dedicated_inference_id}/accelerators/{accelerator_id}.
dedicated_inferences_list_accelerators	select	dedicated_inference_id	per_page, page, slug	List all accelerators (GPUs) in use by a Dedicated Inference instance. Send a GET request to /v2/dedicated-inferences/{dedicated_inference_id}/accelerators. Optionally filter by slug and use page/per_page for pagination.

Parameters

Parameters can be passed in the WHERE clause of a query. Check the Methods section to see which parameters are required or optional for each operation.

Name	Datatype	Description
accelerator_id	string (uuid)	A unique identifier for a Dedicated Inference accelerator. (example: 5b5c619c-359c-44ca-87e2-47e98170c02f)
dedicated_inference_id	string (uuid)	A unique identifier for a Dedicated Inference instance. (example: 6b5c619c-359c-44ca-87e2-47e98170c01d)
page	integer	Which 'page' of paginated results to return. (example: 1)
per_page	integer	Number of items returned per page (example: 20)
slug	string	Filter accelerators by GPU slug. (example: gpu-mi300x1-192gb)

SELECT examples

dedicated_inferences_get_accelerator

Retrieve a single accelerator by ID for a Dedicated Inference instance. Send a
GET request to /v2/dedicated-inferences/{dedicated_inference_id}/accelerators/{accelerator_id}.

SELECT
id,
name,
created_at,
role,
slug,
status
FROM digitalocean.inference.dedicated_inference_accelerators
WHERE dedicated_inference_id = '{{ dedicated_inference_id }}' -- required
AND accelerator_id = '{{ accelerator_id }}' -- required
;

dedicated_inferences_list_accelerators

List all accelerators (GPUs) in use by a Dedicated Inference instance. Send a
GET request to /v2/dedicated-inferences/{dedicated_inference_id}/accelerators.
Optionally filter by slug and use page/per_page for pagination.

SELECT
id,
name,
created_at,
role,
slug,
status
FROM digitalocean.inference.dedicated_inference_accelerators
WHERE dedicated_inference_id = '{{ dedicated_inference_id }}' -- required
AND per_page = '{{ per_page }}'
AND page = '{{ page }}'
AND slug = '{{ slug }}'
;