Closed Bob123Yang closed 2 weeks ago
yes, the submission
variation turns on all the modes as given here
@Bob123Yang Can you please share the compilation error mentioned in the title? The compilation of nvidia-harness is not tested on a wide variety of systems and it is recommended to us this docker setup for running nvidia-harness.
Hi @Bob123Yang . Did this command work for you? Should we close this ticket? Thanks!
Closing this issue for now. Please reopen if required.
Do full accuracy and performance runs for all the scenarios with below commands:
cmr "generate-run-cmds inference _submission _all-scenarios" --model=rnnt \ --device=cuda --implementation=nvidia-original --backend=tensorrt \ --execution-mode=valid --results_dir=$HOME/results_dir \ --category=edge --division=open --quiet