onnx_diagnostic.reference.torch_ops.generator_ops¶

class onnx_diagnostic.reference.torch_ops.generator_ops.Range_11(node: NodeProto, version: int | None = None, device: device | None = None, verbose: int = 0)[source][source]¶

Range

classmethod device_dependent() → bool[source][source]¶: Returns True if the kernel needs a device to be efficiently initialized.

run(starts: OpRunTensor, limit: OpRunTensor, delta: OpRunTensor) → OpRunTensor[source][source]¶: Kernel implementation.