Skip to content

vllm.config.utils

ConfigT module-attribute

ConfigT = TypeVar('ConfigT', bound=ConfigType)

ConfigType module-attribute

ConfigType = type[DataclassInstance]

config

config(cls: ConfigT) -> ConfigT

A decorator that ensures all fields in a dataclass have default values and that each field has a docstring.

If a ConfigT is used as a CLI argument itself, the type keyword argument provided by get_kwargs will be pydantic.TypeAdapter(ConfigT).validate_json(cli_arg) which treats the cli_arg as a JSON string which gets validated by pydantic.

Config validation is performed by the tools/validate_config.py script, which is invoked during the pre-commit checks.

Source code in vllm/config/utils.py
def config(cls: ConfigT) -> ConfigT:
    """
    A decorator that ensures all fields in a dataclass have default values
    and that each field has a docstring.

    If a `ConfigT` is used as a CLI argument itself, the `type` keyword argument
    provided by `get_kwargs` will be
    `pydantic.TypeAdapter(ConfigT).validate_json(cli_arg)` which treats the
    `cli_arg` as a JSON string which gets validated by `pydantic`.

    Config validation is performed by the tools/validate_config.py
    script, which is invoked during the pre-commit checks.
    """
    return cls