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

enqueue_apple_matmul

def enqueue_apple_matmul[in_type: DType, c_type: DType = DType.float32, transpose_b: Bool = False, elementwise_lambda_fn: Optional[def[dtype: DType, width: Int, *, alignment: Int = 1](IndexList[2], SIMD[dtype, width]) capturing -> None] = None](c: TileTensor[c_type, address_space=c.address_space, linear_idx_type=c.linear_idx_type, element_size=c.element_size], a: TileTensor[in_type, address_space=a.address_space, linear_idx_type=a.linear_idx_type, element_size=a.element_size], b: TileTensor[in_type, address_space=b.address_space, linear_idx_type=b.linear_idx_type, element_size=b.element_size], ctx: DeviceContext)

Enqueue the Apple M5 matmul kernel on the given device context.

Accepts row-major TileTensor operands. For transpose_b=True, B is expected with shape (N, K).

Raises:

If the attached GPU is not Apple M5 (compute_capability != 5). M1-M4 lack GPU neural accelerator; future generations require re-validation.