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 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€‹

AnyType, Deinitable, Movable

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__()

Was this page helpful?