📦
Version0.23.0
Revision21
Size170.0 MB
Licenseunset
Confinementclassic
Basecore18

A machine learning benchmarking toolkit


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

Update History

0.23.0 (21)
1 Apr 2026, 21:28 UTC

Published27 Jun 2021, 03:41 UTC

Last updated21 Jul 2023, 17:48 UTC

First seen1 Apr 2026, 21:28 UTC