search

mlcommons / ck

Collective Mind (CM) is a small, modular, cross-platform and decentralized workflow automation framework with a human-friendly interface and reusable automation recipes to make it easier to build, run, benchmark and optimize AI, ML and other applications and systems across diverse and continuously changing models, data, software and hardware
https://cKnowledge.org/install-cm-mlops
Apache License 2.0
600 stars 111 forks source link

rnnt complie error on TensorRT #1021

Closed Bob123Yang closed 2 weeks ago

Bob123Yang commented 10 months ago

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

arjunsuresh commented 10 months 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.

gfursin commented 8 months ago

Hi @Bob123Yang . Did this command work for you? Should we close this ticket? Thanks!

arjunsuresh commented 2 weeks ago

Closing this issue for now. Please reopen if required.