Mojo function

grouped_matmul_sm100_persistent

grouped_matmul_sm100_persistent[c_type: DType, a_type: DType, b_type: DType, transpose_b: Bool, *, config: MatmulConfig[a_type, b_type, c_type, transpose_b], cta_group: Int = 1, num_pipeline_stages: Optional[UInt] = None, a_swizzle: TensorMapSwizzle = TensorMapSwizzle.SWIZZLE_128B, b_swizzle: TensorMapSwizzle = TensorMapSwizzle.SWIZZLE_128B, elementwise_lambda_fn: Optional[def[dtype: DType, width: Int, *, alignment: Int = 1](IndexList[2], SIMD[dtype, width]) capturing -> None] = None](c: TileTensor[c_type, c.LayoutType, c.origin, linear_idx_type=c.linear_idx_type, element_size=c.element_size], a: TileTensor[a_type, a.LayoutType, a.origin, linear_idx_type=a.linear_idx_type, element_size=a.element_size], a_offsets: TileTensor[DType.uint32, a_offsets.LayoutType, a_offsets.origin, linear_idx_type=a_offsets.linear_idx_type, element_size=a_offsets.element_size], max_num_tokens_per_expert: Int, b: TileTensor[b_type, b.LayoutType, b.origin, linear_idx_type=b.linear_idx_type, element_size=b.element_size], expert_ids: TileTensor[DType.int32, expert_ids.LayoutType, expert_ids.origin, linear_idx_type=expert_ids.linear_idx_type, element_size=expert_ids.element_size], num_active_experts: Int, ctx: DeviceContext)