nim_metadata

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

Overview

Name	nim_metadata
Type	Resource
Id	nvidia.catalog.nim_metadata

Fields

The following fields are returned by SELECT queries:

SELECT not supported for this resource, use SHOW METHODS to view available operations for the resource.

Methods

The following methods are available for this resource:

Name	Accessible by	Required Params	Optional Params	Description
create	insert	team, nim_name, tag		Registers NIM profile metadata for the given team, NIM name, and tag. This is a placeholder that validates the supplied profiles and echoes the provided fields back to the caller.<br />SSA: requires the following scope createNimMetadata<br />

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
nim_name	string (UTF-8)	NIM name
tag	string (UTF-8)	NIM tag
team	string (UTF-8)	Team name

INSERT examples

create

Registers NIM profile metadata for the given team, NIM name, and tag. This is a placeholder that validates the supplied profiles and echoes the provided fields back to the caller.<br />SSA: requires the following scope createNimMetadata<br />

INSERT INTO nvidia.catalog.nim_metadata (
profiles,
team,
nim_name,
tag
)
SELECT 
'{{ profiles }}',
'{{ team }}',
'{{ nim_name }}',
'{{ tag }}'
RETURNING
profiles
;

Manifest

# Description fields are for documentation purposes
- name: nim_metadata
props:
  - name: team
    value: "{{ team }}"
    description: Required parameter for the nim_metadata resource.
  - name: nim_name
    value: "{{ nim_name }}"
    description: Required parameter for the nim_metadata resource.
  - name: tag
    value: "{{ tag }}"
    description: Required parameter for the nim_metadata resource.
  - name: profiles
    value:
      - buildable_profile: {{ buildable_profile }}
        checksum: "{{ checksum }}"
        feat_lora: {{ feat_lora }}
        form_factor: "{{ form_factor }}"
        gpu: "{{ gpu }}"
        gpu_device: "{{ gpu_device }}"
        inference_backend: "{{ inference_backend }}"
        latency: "{{ latency }}"
        min_vram_per_device_gb: {{ min_vram_per_device_gb }}
        pipeline_parallel_size: {{ pipeline_parallel_size }}
        precision: "{{ precision }}"
        profile_id: "{{ profile_id }}"
        tensor_parallel_size: {{ tensor_parallel_size }}
        workspace_hash: "{{ workspace_hash }}"