Mojo module

managed_tensor_slice

Implements the ManagedTensorSlice type - a view of a tensor that doesn't own the underlying data. This type is used to build custom graph operations.

`comptime` values

`DynamicTensor`

comptime DynamicTensor[dtype: DType, rank: Int] = ManagedTensorSlice[IOUnknown, static_spec=_get_unknown_tensor_spec[dtype, rank]()]

Parameters

dtype (DType):
rank (Int):

`InputTensor`

comptime InputTensor = ManagedTensorSlice[Input, static_spec=?]

`InputVariadicTensors`

comptime InputVariadicTensors = VariadicTensors[?, Input, static_specs=?]

`OutputTensor`

comptime OutputTensor = ManagedTensorSlice[Output, static_spec=?]

`OutputVariadicTensors`

comptime OutputVariadicTensors = VariadicTensors[?, Output, static_specs=?]

Structs

ManagedTensorSlice: A view of a tensor that does not own the underlying allocated pointer. When the object lifetime ends it does not free the underlying pointer. Conversely, if a ManagedTensorSlice is created, it will not extend the life of the underlying pointer.
StaticTensorSpecList: A statically indexable list of data that can be assembled into a StaticTensorSpecList on demand. This handles the complexities that arise with heterogenous specs.
VariadicTensors: A tuple-like container of tensors representing variadic arguments from the graph compiler.

Functions

foreach: Apply the function func to each element of the tensor slice.
trace_slice_arg: Helper to stringify the type and shape of a kernel argument for tracing.

comptime values​

DynamicTensor​

Parameters​

InputTensor​

InputVariadicTensors​

OutputTensor​

OutputVariadicTensors​

Structs​

Functions​