vllm_omni.worker_v2.first_audio_sender ¶

Deliver in-stage first audio as soon as its device copy completes.

The regular output of a step is published only after the whole step's outputs are copied, materialized for every request, popped by the engine loop and serialized together. A stream's first audio chunk does not need any of that, so a dedicated thread waits for the chunk's own copy event and hands a one-request output straight to the engine core's output queue.

logger `module-attribute` ¶

logger = init_logger(__name__)

FirstAudioSender ¶

close ¶

close() -> None

submit ¶

submit(
    request_ids: list[str],
    pcm: Tensor,
    sample_rate: Tensor,
    valid: Tensor | None = None,
) -> list[str]

Queue a D2H copy of pcm [n, samples] on the current stream and deliver it once done.

valid [n] (on device) drops rows whose frame turned out not to be audio (e.g. a codec EOS sample); it is read only after the copy.

Return the request IDs whose delivery was accepted. Rows without an engine output route must retain regular codec delivery instead of promising the orchestrator a first frame that can never arrive.

FirstAudioSink ¶

Bases: Protocol

prepare ¶

prepare(request_ids: list[str]) -> _PreparedDelivery

Freeze request routes on the submitting thread before accepting delivery.

engine_output_queue_sink ¶

engine_output_queue_sink(
    output_queue: Any,
    scheduler: Any,
    *,
    upstream_first_audio: bool = True,
) -> _EngineOutputSink

Route prepared audio; final-stage PCM must not carry the upstream marker.