package
0.0.9
Repository: https://github.com/inftyai/llmaz.git
Documentation: pkg.go.dev

# Functions

Resource is required by pkg/client/listers/...

# Constants

DraftRole represents the draft model in speculative decoding, the main model is the target model then.
No description provided by the author
LoraRole represents the lora model.
MainRole represents the main model, if only one model is required, it must be the main model.
No description provided by the author
No description provided by the author
No description provided by the author
ModelPending means model is waiting for model downloading.
Annotation with value = "true" represents we'll preload the model, by default via Manta(https://github.com/InftyAI/Manta), make sure Manta is installed in prior.
ModelReady means model is already downloaded.

# Variables

AddToScheme adds the types in this group-version to the given scheme.
GroupVersion is group version used to register these objects.
SchemeBuilder is used to add go types to the GroupVersionKind scheme.
SchemeGroupVersion is alias to GroupVersion for client-go libraries.

# Structs

Flavor defines the accelerator requirements for a model and the necessary parameters in autoscaling.
ModelClaim represents claiming for one model, it's the standard claimMode of multiModelsClaim compared to other modes like SpeculativeDecoding.
ModelClaims represents multiple claims for different models.
ModelHub represents the model registry for model downloads.
ModelRefer refers to a created Model with it's role.
ModelSource represents the source of the model.
ModelSpec defines the desired state of Model.
ModelStatus defines the observed state of Model.
OpenModel is the Schema for the open models API.
OpenModelList contains a list of OpenModel.

# Type aliases

No description provided by the author
No description provided by the author
No description provided by the author
URIProtocol represents the protocol of the URI.