fastvideo.worker.executor

Module Contents

Classes

Executor

Data

logger

API

class fastvideo.worker.executor.Executor(fastvideo_args: fastvideo.fastvideo_args.FastVideoArgs)

Bases: abc.ABC

abstract collective_rpc(method: str | collections.abc.Callable[..., fastvideo.worker.executor._R], timeout: float | None = None, args: tuple = (), kwargs: dict[str, Any] | None = None) → list[fastvideo.worker.executor._R]

Execute an RPC call on all workers.

Parameters:

• method –

  Name of the worker method to execute, or a callable that is serialized and sent to all workers to execute.

  If the method is a callable, it should accept an additional self argument, in addition to the arguments passed in args and kwargs. The self argument will be the worker object.

• timeout –

  Maximum time in seconds to wait for execution. Raises a

  exc:

  TimeoutError on timeout. None means wait indefinitely.

• args – Positional arguments to pass to the worker method.

• kwargs – Keyword arguments to pass to the worker method.

Returns:

A list containing the results from each worker.

.. note::

It is recommended to use this API to only pass control messages, and set up data-plane communication to pass data.

execute_forward(forward_batch: fastvideo.pipelines.ForwardBatch, fastvideo_args: fastvideo.fastvideo_args.FastVideoArgs) → fastvideo.pipelines.ForwardBatch

classmethod get_class(fastvideo_args: fastvideo.fastvideo_args.FastVideoArgs) → type[fastvideo.worker.executor.Executor]

abstract merge_lora_weights() → None

Merge the LoRA weights for the workers.

abstract set_lora_adapter(lora_nickname: str, lora_path: str | None = None) → None

Set the LoRA adapter for the workers.

abstract shutdown() → None

Shutdown the executor.

abstract unmerge_lora_weights() → None

Unmerge the LoRA weights for the workers.

fastvideo.worker.executor.logger

‘init_logger(…)’