Perftest: explicitly include standard C++ library Perftest: Make cudart linkage optional due to nvcc and GCC incompatibility Perftest: add cudart support info to README Fixed loss of one payload part due to skip of one address Perftest: Fix perform warm up process stuck Two bugfixes Perftest: Do not align SRQ recv length to MTU for hns Cuda: Use pcie mapping regardless of data direct Add support for DMA-buffers in Cambricon devices Perftest supports MLU latency tests with read/send verbs only Perftest: Add GitHub actions support Perftest: Add null-mr support over server side Added TCU support add Yunsilicon dev types Perftest: disable Scatter2CQE with gpudirect send_lat Perftest: fix OOO_RECV_WRS enablement flow Perftest: Add print in case blueflame is not supported Perftest: Version increase to 6.26 Perftest: changing spec file version to 25.07.0 Perftest: Dynamic CUDA linking