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