experimental_experiment.torch_interpreter.eval.model_cases

class experimental_experiment.torch_interpreter.eval.model_cases.AtenAsStrided

forward(x)

Define the computation performed at every call.

Should be overridden by all subclasses.

Note

Although the recipe for forward pass needs to be defined within this function, one should call the Module instance afterwards instead of this since the former takes care of running the registered hooks while the latter silently ignores them.

class experimental_experiment.torch_interpreter.eval.model_cases.AtenInterpolate(*args: Any, **kwargs: Any)

forward(x)

Define the computation performed at every call.

Should be overridden by all subclasses.

Note

Although the recipe for forward pass needs to be defined within this function, one should call the Module instance afterwards instead of this since the former takes care of running the registered hooks while the latter silently ignores them.

class experimental_experiment.torch_interpreter.eval.model_cases.AtenNonZero(*args: Any, **kwargs: Any)

forward(x)

Define the computation performed at every call.

Should be overridden by all subclasses.

Note

Although the recipe for forward pass needs to be defined within this function, one should call the Module instance afterwards instead of this since the former takes care of running the registered hooks while the latter silently ignores them.

class experimental_experiment.torch_interpreter.eval.model_cases.AtenNonZeroTuple(*args: Any, **kwargs: Any)

forward(x)

Define the computation performed at every call.

Should be overridden by all subclasses.

Note

Although the recipe for forward pass needs to be defined within this function, one should call the Module instance afterwards instead of this since the former takes care of running the registered hooks while the latter silently ignores them.

class experimental_experiment.torch_interpreter.eval.model_cases.AtenRollPos(*args: Any, **kwargs: Any)

forward(x)

Define the computation performed at every call.

Should be overridden by all subclasses.

Note

Although the recipe for forward pass needs to be defined within this function, one should call the Module instance afterwards instead of this since the former takes care of running the registered hooks while the latter silently ignores them.

class experimental_experiment.torch_interpreter.eval.model_cases.AtenRollRelu(*args: Any, **kwargs: Any)

forward(x)

Define the computation performed at every call.

Should be overridden by all subclasses.

Note

Although the recipe for forward pass needs to be defined within this function, one should call the Module instance afterwards instead of this since the former takes care of running the registered hooks while the latter silently ignores them.

class experimental_experiment.torch_interpreter.eval.model_cases.BuildInIsInstance(n_dims: int = 3, n_targets: int = 1)

forward(x, lx: list | Tensor)

Define the computation performed at every call.

Should be overridden by all subclasses.

Note

Although the recipe for forward pass needs to be defined within this function, one should call the Module instance afterwards instead of this since the former takes care of running the registered hooks while the latter silently ignores them.

class experimental_experiment.torch_interpreter.eval.model_cases.BuildInLen(n_dims: int = 3, n_targets: int = 1)

forward(x, lx: list)

Define the computation performed at every call.

Should be overridden by all subclasses.

Note

Although the recipe for forward pass needs to be defined within this function, one should call the Module instance afterwards instead of this since the former takes care of running the registered hooks while the latter silently ignores them.

class experimental_experiment.torch_interpreter.eval.model_cases.ComplexPolar(*args: Any, **kwargs: Any)

forward(x, angle)

Define the computation performed at every call.

Should be overridden by all subclasses.

Note

Although the recipe for forward pass needs to be defined within this function, one should call the Module instance afterwards instead of this since the former takes care of running the registered hooks while the latter silently ignores them.

class experimental_experiment.torch_interpreter.eval.model_cases.ControlFlowCond(*args: Any, **kwargs: Any)

forward(x)

Define the computation performed at every call.

Should be overridden by all subclasses.

Note

Although the recipe for forward pass needs to be defined within this function, one should call the Module instance afterwards instead of this since the former takes care of running the registered hooks while the latter silently ignores them.

class experimental_experiment.torch_interpreter.eval.model_cases.ControlFlowCond2Inputs(*args: Any, **kwargs: Any)

forward(x, y)

Define the computation performed at every call.

Should be overridden by all subclasses.

Note

Although the recipe for forward pass needs to be defined within this function, one should call the Module instance afterwards instead of this since the former takes care of running the registered hooks while the latter silently ignores them.

class experimental_experiment.torch_interpreter.eval.model_cases.ControlFlowCond2Outputs(*args: Any, **kwargs: Any)

forward(x)

Define the computation performed at every call.

Should be overridden by all subclasses.

Note

Although the recipe for forward pass needs to be defined within this function, one should call the Module instance afterwards instead of this since the former takes care of running the registered hooks while the latter silently ignores them.

class experimental_experiment.torch_interpreter.eval.model_cases.ControlFlowCondConstant(*args: Any, **kwargs: Any)

forward(x)

Define the computation performed at every call.

Should be overridden by all subclasses.

Note

Although the recipe for forward pass needs to be defined within this function, one should call the Module instance afterwards instead of this since the former takes care of running the registered hooks while the latter silently ignores them.

class experimental_experiment.torch_interpreter.eval.model_cases.ControlFlowCondNestedModule

class Submodule

forward(x)

Define the computation performed at every call.

Should be overridden by all subclasses.

Note

Although the recipe for forward pass needs to be defined within this function, one should call the Module instance afterwards instead of this since the former takes care of running the registered hooks while the latter silently ignores them.

forward(x)

Define the computation performed at every call.

Should be overridden by all subclasses.

Note

Although the recipe for forward pass needs to be defined within this function, one should call the Module instance afterwards instead of this since the former takes care of running the registered hooks while the latter silently ignores them.

class experimental_experiment.torch_interpreter.eval.model_cases.ControlFlowNestCond(*args: Any, **kwargs: Any)

forward(x)

Define the computation performed at every call.

Should be overridden by all subclasses.

Note

Although the recipe for forward pass needs to be defined within this function, one should call the Module instance afterwards instead of this since the former takes care of running the registered hooks while the latter silently ignores them.

class experimental_experiment.torch_interpreter.eval.model_cases.ControlFlowScan(*args: Any, **kwargs: Any)

static add(carry: Tensor, y: Tensor)

forward(x)

Define the computation performed at every call.

Should be overridden by all subclasses.

Note

Although the recipe for forward pass needs to be defined within this function, one should call the Module instance afterwards instead of this since the former takes care of running the registered hooks while the latter silently ignores them.

class experimental_experiment.torch_interpreter.eval.model_cases.ControlFlowScan2Carried(*args: Any, **kwargs: Any)

static add(carry1: Tensor, carry2: Tensor, y1: Tensor, y2: Tensor)

forward(x)

Define the computation performed at every call.

Should be overridden by all subclasses.

Note

Although the recipe for forward pass needs to be defined within this function, one should call the Module instance afterwards instead of this since the former takes care of running the registered hooks while the latter silently ignores them.

class experimental_experiment.torch_interpreter.eval.model_cases.ControlFlowScanCDist(*args: Any, **kwargs: Any)

static dist(carry: Tensor, x: Tensor)

forward(x)

Define the computation performed at every call.

Should be overridden by all subclasses.

Note

Although the recipe for forward pass needs to be defined within this function, one should call the Module instance afterwards instead of this since the former takes care of running the registered hooks while the latter silently ignores them.

class experimental_experiment.torch_interpreter.eval.model_cases.ControlFlowScanCDist2(*args: Any, **kwargs: Any)

static dist(unused: Tensor, x: Tensor, samex: Tensor)

forward(x)

Define the computation performed at every call.

Should be overridden by all subclasses.

Note

Although the recipe for forward pass needs to be defined within this function, one should call the Module instance afterwards instead of this since the former takes care of running the registered hooks while the latter silently ignores them.

class experimental_experiment.torch_interpreter.eval.model_cases.ControlFlowScanCDistXY(*args: Any, **kwargs: Any)

static dist(y: Tensor, scanned_x: Tensor)

forward(x, y)

Define the computation performed at every call.

Should be overridden by all subclasses.

Note

Although the recipe for forward pass needs to be defined within this function, one should call the Module instance afterwards instead of this since the former takes care of running the registered hooks while the latter silently ignores them.

class experimental_experiment.torch_interpreter.eval.model_cases.CropLastDimensionWithTensorContent(*args: Any, **kwargs: Any)

forward(x, shape)

Define the computation performed at every call.

Should be overridden by all subclasses.

Note

Although the recipe for forward pass needs to be defined within this function, one should call the Module instance afterwards instead of this since the former takes care of running the registered hooks while the latter silently ignores them.

class experimental_experiment.torch_interpreter.eval.model_cases.CropLastDimensionWithTensorShape(*args: Any, **kwargs: Any)

forward(x, y)

Define the computation performed at every call.

Should be overridden by all subclasses.

Note

Although the recipe for forward pass needs to be defined within this function, one should call the Module instance afterwards instead of this since the former takes care of running the registered hooks while the latter silently ignores them.

class experimental_experiment.torch_interpreter.eval.model_cases.InplaceAdd

forward(x)

Define the computation performed at every call.

Should be overridden by all subclasses.

Note

Although the recipe for forward pass needs to be defined within this function, one should call the Module instance afterwards instead of this since the former takes care of running the registered hooks while the latter silently ignores them.

class experimental_experiment.torch_interpreter.eval.model_cases.InplaceAdd_

forward(x)

Define the computation performed at every call.

Should be overridden by all subclasses.

Note

Although the recipe for forward pass needs to be defined within this function, one should call the Module instance afterwards instead of this since the former takes care of running the registered hooks while the latter silently ignores them.

class experimental_experiment.torch_interpreter.eval.model_cases.InplaceAdd_Mul

forward(x)

Define the computation performed at every call.

Should be overridden by all subclasses.

Note

Although the recipe for forward pass needs to be defined within this function, one should call the Module instance afterwards instead of this since the former takes care of running the registered hooks while the latter silently ignores them.

class experimental_experiment.torch_interpreter.eval.model_cases.InplaceCloneAdd_

forward(x)

Define the computation performed at every call.

Should be overridden by all subclasses.

Note

Although the recipe for forward pass needs to be defined within this function, one should call the Module instance afterwards instead of this since the former takes care of running the registered hooks while the latter silently ignores them.

class experimental_experiment.torch_interpreter.eval.model_cases.InplaceSetItemEllipsis_1

forward(index, update)

Define the computation performed at every call.

Should be overridden by all subclasses.

Note

Although the recipe for forward pass needs to be defined within this function, one should call the Module instance afterwards instead of this since the former takes care of running the registered hooks while the latter silently ignores them.

class experimental_experiment.torch_interpreter.eval.model_cases.InplaceSetItemEllipsis_2

forward(index, update)

Define the computation performed at every call.

Should be overridden by all subclasses.

Note

Although the recipe for forward pass needs to be defined within this function, one should call the Module instance afterwards instead of this since the former takes care of running the registered hooks while the latter silently ignores them.

class experimental_experiment.torch_interpreter.eval.model_cases.InplaceSetItemMask(*args: Any, **kwargs: Any)

forward(x)

Define the computation performed at every call.

Should be overridden by all subclasses.

Note

Although the recipe for forward pass needs to be defined within this function, one should call the Module instance afterwards instead of this since the former takes care of running the registered hooks while the latter silently ignores them.

class experimental_experiment.torch_interpreter.eval.model_cases.InplaceSetItemSquare(*args: Any, **kwargs: Any)

forward(x)

Define the computation performed at every call.

Should be overridden by all subclasses.

Note

Although the recipe for forward pass needs to be defined within this function, one should call the Module instance afterwards instead of this since the former takes care of running the registered hooks while the latter silently ignores them.

class experimental_experiment.torch_interpreter.eval.model_cases.InplaceSetItemSquareAdd(*args: Any, **kwargs: Any)

forward(x)

Define the computation performed at every call.

Should be overridden by all subclasses.

Note

Although the recipe for forward pass needs to be defined within this function, one should call the Module instance afterwards instead of this since the former takes care of running the registered hooks while the latter silently ignores them.

class experimental_experiment.torch_interpreter.eval.model_cases.InplaceSetItemSquareAdd2(*args: Any, **kwargs: Any)

forward(x)

Define the computation performed at every call.

Should be overridden by all subclasses.

Note

Although the recipe for forward pass needs to be defined within this function, one should call the Module instance afterwards instead of this since the former takes care of running the registered hooks while the latter silently ignores them.

class experimental_experiment.torch_interpreter.eval.model_cases.SignatureFloat1(n_dims: int = 3, n_targets: int = 1)

forward(x, alpha: float = 2.0)

Define the computation performed at every call.

Should be overridden by all subclasses.

Note

Although the recipe for forward pass needs to be defined within this function, one should call the Module instance afterwards instead of this since the former takes care of running the registered hooks while the latter silently ignores them.

class experimental_experiment.torch_interpreter.eval.model_cases.SignatureInt1(n_dims: int = 3, n_targets: int = 1)

forward(x, i: int = 2)

Define the computation performed at every call.

Should be overridden by all subclasses.

Note

Although the recipe for forward pass needs to be defined within this function, one should call the Module instance afterwards instead of this since the former takes care of running the registered hooks while the latter silently ignores them.

class experimental_experiment.torch_interpreter.eval.model_cases.SignatureInt2(n_dims: int = 3, n_targets: int = 1)

forward(x, i: int = 2)

Define the computation performed at every call.

Should be overridden by all subclasses.

Note

Although the recipe for forward pass needs to be defined within this function, one should call the Module instance afterwards instead of this since the former takes care of running the registered hooks while the latter silently ignores them.

class experimental_experiment.torch_interpreter.eval.model_cases.SignatureListFixedLength(n_dims: int = 3, n_targets: int = 1)

forward(x, lx: list)

Define the computation performed at every call.

Should be overridden by all subclasses.

Note

Although the recipe for forward pass needs to be defined within this function, one should call the Module instance afterwards instead of this since the former takes care of running the registered hooks while the latter silently ignores them.

class experimental_experiment.torch_interpreter.eval.model_cases.SignatureListVariableLength(n_dims: int = 3, n_targets: int = 1)

forward(x, lx: list)

Define the computation performed at every call.

Should be overridden by all subclasses.

Note

Although the recipe for forward pass needs to be defined within this function, one should call the Module instance afterwards instead of this since the former takes care of running the registered hooks while the latter silently ignores them.

class experimental_experiment.torch_interpreter.eval.model_cases.SignatureShapeAsIndex(n_dims: int = 3, n_targets: int = 1)

forward(x, y)

Define the computation performed at every call.

Should be overridden by all subclasses.

Note

Although the recipe for forward pass needs to be defined within this function, one should call the Module instance afterwards instead of this since the former takes care of running the registered hooks while the latter silently ignores them.

class experimental_experiment.torch_interpreter.eval.model_cases.TypeBFloat16(*args: Any, **kwargs: Any)

forward(x)

Define the computation performed at every call.

Should be overridden by all subclasses.

Note

Although the recipe for forward pass needs to be defined within this function, one should call the Module instance afterwards instead of this since the former takes care of running the registered hooks while the latter silently ignores them.