For the complete documentation index, see llms.txt. Markdown versions of all pages are available by appending .md to any URL (e.g. /max/get-started.md).

Mojo function

zero_output

def zero_output[c_type: DType, *, output_tile_shape: IndexList[Int(2)], c_stride: Int, c_N: Int](c_ptr: Pointer[Scalar[c_type], MutAnyOrigin, _safe=False], coord: Tuple[UInt32, UInt32], group_end_idx: UInt32)

Zero-fills an output tile for skipped or invalid expert assignments.

Each thread stores a SIMD vector of zeros per row across the output tile width, masking out threads and rows that fall outside the valid tile or group boundary.

Parameters:

c_type (DType): Element type of the C output tensor.
output_tile_shape (IndexList[Int(2)]): Tile shape [rows, cols] of the output region to zero-fill, where index 0 bounds the row count and index 1 bounds the column count.
c_stride (Int): Row stride of the C output tensor in elements; the store pointer advances by this amount per row.
c_N (Int): Total width of the C output tensor in elements; bounds the column offset coord[0] to mask out-of-bound stores.

Args:

c_ptr (Pointer[Scalar[c_type], MutAnyOrigin, _safe=False]): Base pointer to the C output tensor in global memory.
coord (Tuple[UInt32, UInt32]): (m, n) element coordinates of the output tile origin, where coord[0] is the column offset and coord[1] is the row offset.
group_end_idx (UInt32): Exclusive end of the current group's valid row range; bounds the number of rows zeroed.