JoachimMoe

Failure when running BERT benchmark on NVIDIA Jetson AGX

14

After following the [official guidelines](https://github.com/mlcommons/ck/blob/master/docs/mlperf/inference/bert/README_nvidia.md) on the NVIDIA Jetson AGX, with a modified run-command, namely: ``` cmr "generate-run-cmds inference _submission _all-scenarios" --model=bert-99 --device=cuda --implementation=nvidia-original --backend=tensorrt --execution-mode=valid --results_dir=$HOME/results_dir --category=edge --division=open --quiet...

Running large inputs results in "Worker process still alive after 3.1999992370605472 seconds, killing"

5

The following program: ``` import cupy as cp import numpy as np import dask.array as da import rmm import sys import time from helpers import * from dask_cuda import LocalCUDACluster...

Running the benchmark on Xavier AGX

1

I am currently trying to execute the different benchmarks on the NVIDIA Jetson Xavier AGX. I have successfully built the container with ```make prebuild``` and ```make build```. This has launched...