Torch Model Archiver is used for creating archives of trained neural net models that can be consumed by TorchServe inference
Project Links
Meta
Author: PyTorch Serving team
Classifiers
Torch Model Archiver is a tool used for creating archives of trained neural net models that can be consumed by TorchServe for inference.
Use the Torch Model Archiver CLI to create a .mar file.
Torch Model Archiver is part of TorchServe. However, you can install Torch Model Archiver stand alone.
Detailed documentation and examples are provided in the README.
Installation
python -m pip install torch-model-archiver
Source code
You can check the latest source code as follows:
git clone https://github.com/pytorch/serve.git
Citation
If you use torchserve in a publication or project, please cite torchserve: https://github.com/pytorch/serve
0.12.0
Sep 30, 2024
0.11.1
Jul 18, 2024
0.11.0
May 16, 2024
0.10.0
Mar 14, 2024
0.9.0
Oct 12, 2023
0.8.2
Aug 28, 2023
0.8.1
Jun 14, 2023
0.8.0
May 11, 2023
0.7.1
Feb 08, 2023
0.7.0
Dec 12, 2022
0.6.1
Nov 14, 2022
0.6.0
May 13, 2022
0.5.3
Mar 01, 2022
0.5.2
Dec 29, 2021
0.5.1
Dec 16, 2021
0.5.0
Nov 19, 2021
0.4.2
Aug 02, 2021
0.4.1
Jul 22, 2021
0.4.0
May 20, 2021
0.3.1
Mar 15, 2021
0.3.0
Dec 17, 2020
0.2.1
Dec 14, 2020
0.2.0
Aug 11, 2020
0.1.1
Jun 09, 2020
0.1.0b20200409
Apr 21, 2020
Wheel compatibility matrix
Files in release
Extras:
None
Dependencies:
enum-compat