ray.serve.llm.CloudMirrorConfig#

pydantic model ray.serve.llm.CloudMirrorConfig[source]#

The configuration for mirroring an LLM model from cloud storage.

PublicAPI (beta): This API is in beta and may change before becoming stable.

field bucket_uri: str | None = None#
field extra_files: List[ExtraFiles] [Optional]#
validator check_uri_format  »  bucket_uri[source]#
classmethod from_file(path: str, **kwargs) → ModelT#

Load a model from a YAML file path.

classmethod parse_yaml(file, **kwargs) → ModelT#
property storage_type: str#

Returns the storage type (‘s3’, ‘gcs’, ‘abfss’, or ‘azure’) based on the URI prefix.