Python class

CompiledModel

`CompiledModel`

class max.experimental.nn.CompiledModel(engine_model, input_slots, output_slots, signal_buffers, unary)

source

Compiled model returned by Module.compile().

Provides two execution paths:

Tensor path — compiled(tensor_a, tensor_b) handles distributed Tensors transparently (unflatten shards, append signals, reconstruct). Used by tests and the high-level API.
Buffer path — compiled.execute_raw(*buffers) passes flat Buffers straight to the engine, auto-appending signal buffers. Returns list[Buffer] with zero Tensor overhead. Used by pipeline execute() methods.

For CUDA graph capture/replay, access compiled.engine_model directly:

compiled.engine_model.capture(key, *all_buffers)
compiled.engine_model.replay(key, *all_buffers)

For multi-GPU capture, append compiled.signal_buffers to the buffer list passed to capture/replay.

Parameters:

property engine_model: Model

source

The underlying Model for capture/replay.

execute_raw(*buffers)

source

Buffer-in, Buffer-out execution (no Tensor wrapping).

Auto-appends signal buffers for multi-GPU collectives.

property signal_buffers: list[Buffer]

source

Signal buffers for multi-GPU collectives (empty for single-GPU).