Mojo function

grouped_matmul_kernel_sm100

grouped_matmul_kernel_sm100[a_type: DType, b_type: DType, c_type: DType, b_layout: Layout, a_tile_rank: Int, a_tile_shape: IndexList[a_tile_rank], a_desc_shape: IndexList[a_tile_rank], b_tile_rank: Int, b_tile_shape: IndexList[b_tile_rank], b_desc_shape: IndexList[b_tile_rank], CLayout: TensorLayout, AOffsetsLayout: TensorLayout, ExpertIdsLayout: TensorLayout, block_tile_shape: IndexList[3], mma_shape: IndexList[3], a_swizzle: TensorMapSwizzle = TensorMapSwizzle.SWIZZLE_128B, b_swizzle: TensorMapSwizzle = TensorMapSwizzle.SWIZZLE_128B, c_swizzle: TensorMapSwizzle = TensorMapSwizzle.SWIZZLE_NONE, transpose_b: Bool = True, num_threads: Int = 128, elementwise_lambda_fn: Optional[elementwise_epilogue_type] = None](a_tma_op: TMATensorTile[a_type, a_tile_rank, a_tile_shape, a_desc_shape], b_tma_op: TMATensorTile[b_type, b_tile_rank, b_tile_shape, b_desc_shape], a_offsets: TileTensor[DType.uint32, AOffsetsLayout, ImmutAnyOrigin], expert_ids: TileTensor[DType.int32, ExpertIdsLayout, ImmutAnyOrigin], c: TileTensor[c_type, CLayout, MutAnyOrigin], num_iters: Int)