2.0.6

ShardConfig

Package: flyte.prefetch

Configuration for model sharding.

class ShardConfig(
    engine: typing.Literal['vllm'],
    args: *args,
)

Create a new model by parsing and validating input data from keyword arguments.

Raises ValidationError if the input data cannot be validated to form a valid model.

self is explicitly positional-only to allow self as a field name.

Parameter Type Description
engine typing.Literal['vllm'] The sharding engine to use (currently only “vllm” is supported).
args *args Arguments for the sharding engine.