djl-bench is a command line tool that allows you to benchmark the
model on all different platforms for single-thread/multi-thread
inference performance.
Currently djl-bench support the models from the following framework:
PyTorch
TensorFlow
Apache MXNet
PaddlePaddle
ONNXRuntime
TensorRT
TensorFlow Lite
XGBoost
LightGBM
Python
Details for DJL Benchmark
License
unset
Last updated
21 July 2023 - latest/stable
This snap hasn't been updated in a while. It might be unmaintained and have stability or security issues.
Snaps are applications packaged with all their dependencies to run on all popular Linux distributions from a single build. They update automatically and roll back gracefully.
Snaps are discoverable and installable from the Snap Store, an app store with an audience of millions.
For versions of Ubuntu between 14.04 LTS (Trusty Tahr) and 15.10 (Wily Werewolf), as well as Ubuntu flavours that don’t include snap by default, snap can be installed from the Ubuntu Software Centre by searching for snapd.
Alternatively, snapd can be installed from the command line:
sudo apt update
sudo apt install snapd
Either log out and back in again, or restart your system, to ensure snap’s paths are updated correctly.
Install DJL Benchmark
To install DJL Benchmark, simply use the following command: