ModelArtifactDe#

class nemo_microservices.types.ModelArtifactDe(*args: Any, **kwargs: Any)

Bases: BaseModel

files_url: str

The location where the artifact files are stored.

status: Literal['created', 'upload_failed', 'upload_completed']

The status of the model artifact.

backend_engine: Literal['nemo', 'trt_llm', 'vllm', 'faster_transformer', 'hugging_face'] | None = None

Types of backend engine.

gpu_arch: str | None = None
precision: Literal['int8', 'bf16', 'fp16', 'fp32'] | None = None

Types of model precision.

tensor_parallelism: int | None = None