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
pack_matmul_b_shape_func
def pack_matmul_b_shape_func[a_type: DType, c_type: DType, transpose_in_0: Bool](b_input: TileTensor[Storage=b_input.Storage, linear_idx_type=b_input.linear_idx_type], kernel_type_m: Int = Int(0)) -> IndexList[Int(2)]
TileTensor primary implementation of pack_matmul_b_shape_func.
Takes kernel_type_m directly instead of extracting it from a_shape
static shape params (0 = dynamic M).
Parameters:
- a_type (
DType): Element type of the A operand of the matmul. - c_type (
DType): Element type of the C output of the matmul. - transpose_in_0 (
Bool): True if the B operand is transposed, stored as[N, K]instead of[K, N].
Args:
- b_input (
TileTensor[Storage=b_input.Storage, linear_idx_type=b_input.linear_idx_type]): Read-only rank-2TileTensorcontaining the B matrix whose padded shape is computed. - kernel_type_m (
Int): M dimension used to select the matmul kernel variant (defaults to 0, meaning dynamic M).
Returns:
Was this page helpful?
Thank you! We'll create more content like this.
Thank you for helping us improve!