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 struct
ConvCPU
struct ConvCPU
Registers the mo.conv graph op for CPU devices.
Two execute overloads under one registration: the graph compiler calls
the fused one when the output has a fused epilogue and the plain one when
it has none. The CPU kernel keeps partial sums in its output buffer, so
the fused form gives the kernel only the output's layout and the kernel
accumulates in a buffer of its own, then the epilogue stores each
finished row into the fused output. The plain form has the kernel write
the output directly. The pair is grandfathered on the graph compiler's
allow list; new kernels declare one execute with a StoreAccess
output.
Implemented traitsโ
Methodsโ
executeโ
static def execute[input_layout: StaticString, filter_layout: StaticString, static_strides: Coord[*static_strides.element_types], static_dilations: Coord[*static_dilations.element_types], static_padding: Coord[*static_padding.element_types], _trace_name: StaticString](output: T, input: T, filter: T, strides: T, dilation: T, paddings: T, num_groups: Scalar, ctx: DeviceContext)
static def execute[input_layout: StaticString, filter_layout: StaticString, static_strides: Coord[*static_strides.element_types], static_dilations: Coord[*static_dilations.element_types], static_padding: Coord[*static_padding.element_types], _trace_name: StaticString](output: T, input: T, filter: T, strides: T, dilation: T, paddings: T, num_groups: Scalar, ctx: DeviceContext) where not conforms_to(T, Fused).__bool__()