API Reference

Packages

• thalamus.cloud/v1alpha1

thalamus.cloud/v1alpha1

Package v1alpha1 contains API Schema definitions for the thalamus.cloud v1alpha1 API group.

Resource Types

• Model
• ModelList

EPPSpec

EPPSpec configures the Endpoint Picker Proxy (EPP).

Appears in:

• ServingSpec

Field	Description	Default	Validation
image string	Image is the container image for the EPP.
args string array	Args are passed directly to the EPP as CLI arguments.		Optional: {}
env EnvVar array	Env defines environment variables for the EPP container.		Optional: {}

EPPType

Underlying type: string

Validation:

• Enum: [llm-d unknown]

Appears in:

• ModelStatus

Field	Description
llm-d
unknown

EngineSpec

EngineSpec configures the inference engine instance.

Appears in:

• ServingSpec

Field	Description	Default	Validation
image string	Image is the container image for the inference engine.
args string array	Args are passed directly to the inference engine as CLI arguments.		Optional: {}
env EnvVar array	Env defines environment variables for the inference engine container.		Optional: {}
resources ResourceRequirements	Resources defines the compute resources required by the inference engine.		Optional: {}

EngineType

Underlying type: string

Validation:

• Enum: [vllm unknown]

Appears in:

• ModelStatus

Field	Description
vllm
unknown

HFWeightsSpec

HFWeightsSpec configures model weights sourced from Hugging Face.

Appears in:

• WeightsSpec

Field	Description	Default	Validation
repoId string	RepoID is the Hugging Face repository ID, e.g. "openai/gpt-oss-120b".
tokenSecret SecretKeySelector	TokenSecret references the key within a Kubernetes secret containing the Hugging Face token.

Model

Model is the Schema for the models API.

Appears in:

• ModelList

Field	Description	Default	Validation
apiVersion string	thalamus.cloud/v1alpha1
kind string	Model
metadata ObjectMeta	Refer to Kubernetes API documentation for fields of metadata.		Optional: {}
spec ModelSpec	spec defines the desired state of the Model.		Required: {}
status ModelStatus	status defines the observed state of the Model.		Optional: {}

ModelList

ModelList contains a list of Model.

Field	Description	Default	Validation
apiVersion string	thalamus.cloud/v1alpha1
kind string	ModelList
metadata ListMeta	Refer to Kubernetes API documentation for fields of metadata.
items Model array

ModelPhase

Underlying type: string

Appears in:

• ModelStatus

Field	Description
Pending
Creating
Ready
Failed

ModelSpec

ModelSpec defines the configuration for the model instance.

Appears in:

• Model

Field	Description	Default	Validation
serving ServingSpec	Serving defines how the model is served.
weights WeightsSpec	Weights defines where the model weights are sourced from.
scheduling SchedulingSpec	Scheduling defines scheduling constraints for the model's pods.		Optional: {}

ModelStatus

ModelStatus defines the observed state of a Model.

Appears in:

• Model

Field	Description	Default	Validation
engineType EngineType	EngineType is the detected inference engine type, derived from the engine image.		Enum: [vllm unknown] Optional: {}
eppType EPPType	EPPType is the detected EPP type, derived from the EPP image.		Enum: [llm-d unknown] Optional: {}
phase ModelPhase	Phase summarizes the current lifecycle state of the model.		Optional: {}
conditions Condition array	Conditions represent the latest observations of the model's state.		Optional: {}

SchedulingSpec

SchedulingSpec defines scheduling constraints for the model's pods.

Appears in:

• ModelSpec

Field	Description	Default	Validation
nodeSelector object (keys:string, values:string)	NodeSelector constrains the nodes onto which the model's pods may be scheduled.		Optional: {}

ServingSpec

ServingSpec defines the serving configuration for the model instance.

Appears in:

• ModelSpec

Field	Description	Default	Validation
engine EngineSpec	Engine configures the inference engine container.
epp EPPSpec	EPP configures the optional Endpoint Picker Proxy.		Optional: {}

WeightsSpec

WeightsSpec defines where the model weights are sourced from.

Appears in:

• ModelSpec

Field	Description	Default	Validation
type WeightsType	Type of the weights source.		Enum: [hf]
hf HFWeightsSpec	HF configures weights sourced from Hugging Face.		Optional: {}

WeightsType

Underlying type: string

Validation:

• Enum: [hf]

Appears in:

• WeightsSpec

Field	Description
hf