optimum/quanto/tensor/weights/qbits.py [266:290]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
            return qlinear(*args, **kwargs)
        elif func is torch.equal:
            input, other = args
            return input.equal(other)
        # Defer to operations dispatcher
        with torch._C.DisableTorchFunctionSubclass():
            return func(*args, **kwargs)

    @classmethod
    def __torch_dispatch__(cls, op, types, args, kwargs=None):
        # Do not use directly op, but rather its overload
        op = op.overloadpacket
        if op is torch.ops.aten.detach:
            t = args[0]
            # Detach is required when copying and deserializing
            inner_tensor_names, meta = t.__tensor_flatten__()
            # Detach inner tensors
            detached_tensors = {}
            for inner_name in inner_tensor_names:
                detached_tensors[inner_name] = op(getattr(t, inner_name))
            return cls.__tensor_unflatten__(detached_tensors, meta, t.size(), t.stride())
        elif op in [torch.ops.aten._to_copy, torch.ops.aten.to]:
            t = args[0]
            dtype = kwargs.pop("dtype", t.dtype)
            device = kwargs.pop("device", t.device)
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -



optimum/quanto/tensor/weights/qbytes.py [268:292]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
            return qlinear(*args, **kwargs)
        elif func is torch.equal:
            input, other = args
            return input.equal(other)
        # Defer to operations dispatcher
        with torch._C.DisableTorchFunctionSubclass():
            return func(*args, **kwargs)

    @classmethod
    def __torch_dispatch__(cls, op, types, args, kwargs=None):
        # Do not use directly op, but rather its overload
        op = op.overloadpacket
        if op is torch.ops.aten.detach:
            t = args[0]
            # Detach is required when copying and deserializing
            inner_tensor_names, meta = t.__tensor_flatten__()
            # Detach inner tensors
            detached_tensors = {}
            for inner_name in inner_tensor_names:
                detached_tensors[inner_name] = op(getattr(t, inner_name))
            return cls.__tensor_unflatten__(detached_tensors, meta, t.size(), t.stride())
        elif op in [torch.ops.aten._to_copy, torch.ops.aten.to]:
            t = args[0]
            dtype = kwargs.pop("dtype", t.dtype)
            device = kwargs.pop("device", t.device)
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -