search

mlcommons / mlperf-automations

This repository contains the automations and scripts used to automate MLPerf benchmarks (mainly MLPerf inference for now)
http://docs.mlcommons.org/mlperf-automations/
Apache License 2.0
0 stars 2 forks source link

Update the CM MLPerf inference docs for CUDA device running on host #14

Open arjunsuresh opened 2 months ago

arjunsuresh commented 2 months ago

We need to update the MLPerf inference docs for native CUDA runs

  1. Add a remark that unless CUDA, cuDNN and TensorRT are available in the environment it is recommended to use the docker option
  2. In the run options specify the flags to pass in the cuDNN and TensorRT run files
anandhu-eng commented 2 months ago

Hi @arjunsuresh , this PR adds the first point.