Vincent-syr
Results
2
comments of
Vincent-syr
serving整体的profiling信息根据宏“PPL_LLM_ENABLE_PROFILING”输出,默认是打开的,算子的profiling信息需要nsight去看,建议跑offline_inference。如果想要单step的kernel profling信息,可以参考https://github.com/openppl-public/ppl.nn/blob/master/tools/pplnn_llm.cc#L819 ,编译时“-DPPLNN_ENABLE_KERNEL_PROFILING=ON”
#17 Mark as same problem on V100