onnx_diagnostic.reference.torch_ops.other_ops

class onnx_diagnostic.reference.torch_ops.other_ops.CastLike_15(node: NodeProto, version: int | None = None, verbose: int = 0)

Cast

run(data: OpRunTensor, like: OpRunTensor) → OpRunTensor

Kernel implementation.

class onnx_diagnostic.reference.torch_ops.other_ops.Cast_6(node: NodeProto, version: int | None = None, verbose: int = 0)

Cast

run(data: OpRunTensor) → OpRunTensor

Kernel implementation.

class onnx_diagnostic.reference.torch_ops.other_ops.Concat_1(node: NodeProto, version: int | None = None, verbose: int = 0)

Concat

run(*data: OpRunTensor) → OpRunTensor

Kernel implementation.

class onnx_diagnostic.reference.torch_ops.other_ops.NonZero_13(node: NodeProto, version: int | None = None, verbose: int = 0, custom_kernels: Dict[Tuple[str, str], type] | None = None)

NonZero

run(x: OpRunTensor) → OpRunTensor

Kernel implementation.

class onnx_diagnostic.reference.torch_ops.other_ops.Tile_6(node: NodeProto, version: int | None = None, verbose: int = 0, custom_kernels: Dict[Tuple[str, str], type] | None = None)

Tile

run(x: OpRunTensor, repeat: OpRunTensor) → OpRunTensor

Kernel implementation.

class onnx_diagnostic.reference.torch_ops.other_ops.Transpose_1(node: NodeProto, version: int | None = None, verbose: int = 0)

Transpose

run(data: OpRunTensor) → OpRunTensor

Kernel implementation.

class onnx_diagnostic.reference.torch_ops.other_ops.Trilu_14(node: NodeProto, version: int | None = None, verbose: int = 0)

Trilu

run(data: OpRunTensor, k: OpRunTensor | None = None) → OpRunTensor

Kernel implementation.

class onnx_diagnostic.reference.torch_ops.other_ops.Where_9(node: NodeProto, version: int | None = None, verbose: int = 0, custom_kernels: Dict[Tuple[str, str], type] | None = None)

Where

run(cond: OpRunTensor, x: OpRunTensor, y: OpRunTensor) → OpRunTensor

Kernel implementation.