Mojo function

grouped_matmul_sm100_persistent

grouped_matmul_sm100_persistent[c_type: DType, c_shape: DimList[c_shape.values], a_type: DType, a_shape: DimList[a_shape.values], b_type: DType, b_shape: DimList[b_shape.values], 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[elementwise_epilogue_type] = None](c: NDBuffer[c_type, MutAnyOrigin, c_shape, DimList.create_unknown[2]()], a: NDBuffer[a_type, ImmutAnyOrigin, a_shape, DimList.create_unknown[2]()], a_offsets: NDBuffer[DType.uint32, ImmutAnyOrigin, DimList.create_unknown[1](), DimList.create_unknown[1]()], max_num_tokens_per_expert: Int, b: NDBuffer[b_type, ImmutAnyOrigin, b_shape, DimList.create_unknown[3]()], expert_ids: NDBuffer[DType.int32, ImmutAnyOrigin, DimList.create_unknown[1](), DimList.create_unknown[1]()], num_active_experts: Int, ctx: DeviceContext)