List ModelDeploymentConfig Versions

GET

https://host.com/apis/models/v2/workspaces/:workspace/deployment-configs/:name/versions

GET

/apis/models/v2/workspaces/:workspace/deployment-configs/:name/versions

$ curl https://host.com/apis/models/v2/workspaces/workspace/deployment-configs/name/versions \
>      -H "Content-Type: application/json"

1 [
2   {
3     "name": "llama-3.1-8b",
4     "workspace": "research_team_alpha",
5     "created_at": "2024-01-15T09:30:00Z",
6     "updated_at": "2024-02-10T14:45:00Z",
7     "entity_version": 1,
8     "engine": "nim",
9     "model_spec": {
10       "model_type": "llm",
11       "model_namespace": "meta-ai",
12       "model_name": "llama-3.1-8b",
13       "model_revision": "v3.1.0",
14       "chat_template": "default_chat_template_v1",
15       "tool_call_config": {
16         "tool_call_parser": "openai",
17         "tool_call_plugin": "research_team_alpha/tool_plugins/v1",
18         "auto_tool_choice": true
19       },
20       "lora_enabled": false
21     },
22     "executor_config": {
23       "gpu": 2,
24       "disk_size": "100Gi",
25       "image_name": "nimservice/llama-runtime",
26       "image_tag": "v3.1.0",
27       "health_check_path": "/v1/health/ready",
28       "additional_envs": {
29         "LOG_LEVEL": "info",
30         "MAX_BATCH_SIZE": "16"
31       },
32       "additional_args": [
33         "--enable-logging"
34       ],
35       "k8s_nim_operator_config": {
36         "resources": {
37           "requests": {
38             "cpu": "4",
39             "memory": "16Gi"
40           },
41           "limits": {
42             "cpu": "8",
43             "memory": "32Gi"
44           }
45         },
46         "tolerations": [
47           {
48             "key": "nvidia.com/gpu",
49             "operator": "Exists",
50             "effect": "NoSchedule"
51           }
52         ],
53         "node_selector": {
54           "node-type": "gpu-node",
55           "zone": "us-west1-a"
56         },
57         "startup_probe_grace_seconds": 600
58       },
59       "override_config": {}
60     },
61     "id": "d4f7a9b2-3c1e-4f8a-9b7d-2e5f6a7c8d9e",
62     "project": "proj/nlp/llama_models",
63     "description": "Initial deployment configuration for LLaMA 3.1 8B model.",
64     "model_entity_id": "meta-ai/llama-3.1-8b"
65   },
66   {
67     "name": "llama-3.1-8b",
68     "workspace": "research_team_alpha",
69     "created_at": "2024-02-20T11:00:00Z",
70     "updated_at": "2024-03-01T16:20:00Z",
71     "entity_version": 2,
72     "engine": "nim",
73     "model_spec": {
74       "model_type": "llm",
75       "model_namespace": "meta-ai",
76       "model_name": "llama-3.1-8b",
77       "model_revision": "v3.1.1",
78       "chat_template": "default_chat_template_v2",
79       "tool_call_config": {
80         "tool_call_parser": "openai",
81         "tool_call_plugin": "research_team_alpha/tool_plugins/v2",
82         "auto_tool_choice": true
83       },
84       "lora_enabled": true
85     },
86     "executor_config": {
87       "gpu": 4,
88       "disk_size": "150Gi",
89       "image_name": "nimservice/llama-runtime",
90       "image_tag": "v3.1.1",
91       "health_check_path": "/v1/health/ready",
92       "additional_envs": {
93         "LOG_LEVEL": "debug",
94         "MAX_BATCH_SIZE": "32"
95       },
96       "additional_args": [
97         "--enable-logging",
98         "--optimize-memory"
99       ],
100       "k8s_nim_operator_config": {
101         "resources": {
102           "requests": {
103             "cpu": "8",
104             "memory": "32Gi"
105           },
106           "limits": {
107             "cpu": "16",
108             "memory": "64Gi"
109           }
110         },
111         "tolerations": [
112           {
113             "key": "nvidia.com/gpu",
114             "operator": "Exists",
115             "effect": "NoSchedule"
116           }
117         ],
118         "node_selector": {
119           "node-type": "gpu-node",
120           "zone": "us-west1-b"
121         },
122         "startup_probe_grace_seconds": 600
123       },
124       "override_config": {}
125     },
126     "id": "e7a1c3d4-5b6f-4a7e-8c9d-0f1a2b3c4d5e",
127     "project": "proj/nlp/llama_models",
128     "description": "Updated deployment config with improved resource allocation.",
129     "model_entity_id": "meta-ai/llama-3.1-8b"
130   }
131 ]

List all versions of a ModelDeploymentConfig.

Path parameters

workspacestringRequired

namestringRequired

Response

Return all versions of a model deployment configuration

namestringformat: "^[\w\-.]+$"<=255 characters

Name of the entity. Name/workspace combo must be unique across all entities. Allowed characters: letters (a-z, A-Z), digits (0-9), underscores, hyphens, and dots.

workspacestringformat: "^[\w\-.]+$"<=255 characters

The workspace of the entity. Allowed characters: letters (a-z, A-Z), digits (0-9), underscores, hyphens, and dots.

created_atdatetime

The timestamp of model entity creation

updated_atdatetime

The timestamp of the last model entity update

entity_versioninteger

Version of this deployment config. Automatically managed.

engineenum

Inference engine selecting the compiler path (nim/vllm/generic)

model_specobject

What model to serve and how — independent of the executor it runs on

executor_configobject

Compute + container settings for the executor the deployment runs on

idstring

Unique identifier for the deployment config

projectstringformat: "^[\w\-./]+$"<=255 characters

The URN of the project associated with this entity.

descriptionstring<=1000 characters

Optional description of the deployment configuration

model_entity_idstring<=255 characters

Optional reference to the base model entity ID for this deployment

Errors

422

Unprocessable Entity Error