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
MatmulCPU
struct MatmulCPU
Registers the mo.matmul 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 accumulates in its output buffer, so the fused
form lends it a buffer of its own, or only the output's shape when a
low-precision output accumulates in the kernel's f32 scratch, and the
epilogue stores each finished tile into the fused output, while 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[transpose_b: Bool, packed_b: Bool, _trace_name: StaticString](c: T, a: T, b: T, ctx: DeviceContext)
static def execute[transpose_b: Bool, packed_b: Bool, _trace_name: StaticString](c: T, a: T, b: T, ctx: DeviceContext)