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
Struct_grouped_matmul_ragged
struct Struct_grouped_matmul_ragged
Registers the matmul.grouped.ragged graph op with the graph compiler.
The output takes a fused elementwise epilogue, so a consumer such as an activation runs in the matmul's store instead of as its own kernel. A value-to-value consumer is applied before the matmul's own store, which keeps the SM100 kernel's TMA store.
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, in which case the matmul writes 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(c: T, a: T, b: T, expert_start_indices: T, expert_ids: T, expert_usage_stats: T, context: DeviceContext)
static def execute(c: T, a: T, b: T, expert_start_indices: T, expert_ids: T, expert_usage_stats: T, context: DeviceContext) where not conforms_to(T, Fused).__bool__()