For the complete documentation index, see llms.txt. Markdown versions of all pages are available by appending .md to any URL (e.g. /get-started.md).

Python function

side_stream

side_stream()

max.graph.ops.sequence.side_stream(inputs, body_fn, *, result_types, stream_id=1)

source

Run a block of ops on a side device stream via mo.sequence.

The body executes on the device stream selected by stream_id (0 is the default stream), overlapping independent work on the main stream. Inputs map 1:1 to the body’s block arguments and the body returns one value per result_types entry. The graph compiler binds the whole body to a side-stream device-context view and inserts the cross-stream synchronization at the boundary, so callers never manage streams or events directly.

Parameters:

• inputs (Sequence[Value[TensorType] | TensorValue | Shape | Dim | HasTensorValue | int | float | integer[Any] | floating[Any] | DLPackArray]) – Values passed into the body, mapped 1:1 to block arguments.
• body_fn (Callable[[...], TensorValue | Iterable[TensorValue]]) – Callable receiving one value per input and returning one value per result_types entry.
• result_types (Sequence[TensorType]) – The body’s output types (one per result).
• stream_id (int) – Device stream to run the body on (0 is the default stream).

Returns:

One TensorValue per result_types entry.

Return type:

list[TensorValue]