LLMModelDeployment

Container deployment settings for an internally hosted LLM model.

imageImage (string)required

Fully qualified container image reference for the model server.

command object

Optional container entrypoint override.

anyOf

• string[]
• null

Array [

string

]

options object

Runtime options converted to command-line flags when the model starts.

property name* object

anyOf

• string
• integer
• number
• boolean
• null

string

args object

Additional command-line arguments appended after rendered runtime options.

anyOf

• string[]
• null

Array [

string

]

portPort (integer)

Default value: 8080

cpu object

Requested CPU amount, such as 500m.

anyOf

• string
• null

string

memory object

Requested memory amount, such as 2Gi.

anyOf

• string
• null

string

gpu object

GPU count request

anyOf

• integer
• null

integer

replicasReplicas (integer)

Default value: 1

health_pathHealth Path (string)

Default value: /healthz

env object

Non-secret environment variables passed to the model container.

property name*string

node_selector object

property name*string

LLMModelDeployment

{
  "image": "string",
  "command": [
    "string"
  ],
  "options": {},
  "args": [
    "string"
  ],
  "port": 8080,
  "cpu": "string",
  "memory": "string",
  "gpu": 0,
  "replicas": 1,
  "health_path": "/healthz",
  "env": {},
  "node_selector": {}
}