IMPORTANT: To view this page as Markdown, append `.md` to the URL (e.g. /get-started.md). For the complete documentation index, see llms.txt.
Skip to main content
For the complete documentation index, see llms.txt. Markdown versions of all pages are available by appending .md to any URL (e.g. /get-started.md).

Mojo trait

InputFusion

Trait for input fusion structs that provide custom load behavior.

Conformers are DevicePassable so a GPU kernel callback can capture the functor. Encoding walks fields via encode_fields, translating host Pointers. ManagedTensorSlice.device_type is LayoutTensor and drops in_fusion; capture the fusion value, not the slice.

Implemented traits​

AnyType, Copyable, Deinitable, DevicePassable, ImplicitlyCopyable, Movable, RegisterPassable, TrivialRegisterPassable

comptime members​

device_type​

comptime device_type = _Self

Required methods​

load​

def load[dtype: DType, rank: Int, simd_width: Int, element_alignment: Int = Int(1)](self, idx: IndexList[rank]) -> SIMD[dtype, simd_width]

Returns:

SIMD[dtype, simd_width]

Provided methods​

get_type_name​

static def get_type_name() -> String

Returns:

String

Was this page helpful?