• Docs >
  • 14. TorchServe on Windows
Shortcuts

14. TorchServe on Windows

14.1. Contents of this Document

14.2. Prerequisites

  • At present, it has only been certified on windows server 2019 however should work fine on Windows 10.

  • Make sure you are an admin user or have admin rights

  • The instruction given here will use anaconda Powershell terminal to install torchserve

  • Install Anaconda as given here

  • Install Git as given here

  • Install openjdk11

    • Download openjdk11

    • Unzip and edit/add environment variables i.e. PATH and JAVA_HOME e.g.

    • Using command line unzip openjdk-11*_bin.zip or using GUI interface

    • Edit system or user profile environment variable PATH value and append path <your-openjdk11-path>\bin to it

  • Install nodejs

    • Download nodejs

    • Post installation make sure nodejs and npm node modules binaries are present in PATH environment variable.

    • You may have to re-start windows if your ‘Anaconda Powershell Prompt’ (APP) is not able to detect npm or nodejs commands

14.3. Install from binaries

NOTE At present, wheels for windows are not available on PyPi. However following steps can also be used if you have prebuilt torchserve wheel for windows.

  • Start ‘Anaconda Powershell Prompt’ (APP) as Admin User i.e. By right click on APP and run following commands

  • git clone https://github.com/pytorch/serve.git

  • cd serve

  • python .\ts_scripts\install_dependencies.py

  • For local wheel file

    • pip install <your-torchserve-wheel-file-name>.whl

  • For PyPi package (N/A at present)

    • pip install torchserve torch-model-archiver

  • Start torchserve torchserve.exe --start --model-store <path-to-model-store>

  • For next steps refer Serving a model

14.4. Install from source

  • Ensure that system or user profile environment variable name JAVA_HOME with value as <your-openjdk11-path> path is present.

  • Install Microsoft Visual C++ Redistributable for Visual Studio 2015, 2017 and 2019

    NOTE ensure that you have restarted system after install above Visual C++ components

  • Ensure that ‘nvidia-smi.exe’ is available in Path environment variable. Usually, it should be available under <your_install_drive>\Program Files\NVIDIA Corporation\NVSMI e.g. C:\Program Files\NVIDIA Corporation\NVSMI, add this path to Path env variable

  • Start ‘Anaconda Powershell Prompt’ (APP) as Admin User i.e. By right click on APP and run following commands

  • git clone https://github.com/pytorch/serve.git

  • pip install click

  • cd serve

14.4.1. For production usage, use commands below:

  • python .\ts_scripts\install_dependencies.py --environment=prod

  • python .\ts_scripts\install_from_src.py

14.4.2. For development purposes, use commands below:

If you plan to develop with TorchServe and change some source code, commands below will help. The install_dependencies script installs few extra dependencies which are needed for development and testing.

  • python .\ts_scripts\install_dependencies.py --environment=dev

  • python .\ts_scripts\install_from_src.py

14.5. Troubleshooting

  • If you are building from source then you may have to change the port number for inference, management and metrics apis as specified in frontend/server/src/test/resources/config.properties, all files in frontend/server/src/test/resources/snapshot/* and frontend/server/src/main/java/org/pytorch/serve/util/ConfigManager.java

  • If curl command fails to execute then run following command on APP (anaconda powershell prompt) Remove-item alias:curl Refer to this SO answer for details.

Docs

Access comprehensive developer documentation for PyTorch

View Docs

Tutorials

Get in-depth tutorials for beginners and advanced developers

View Tutorials

Resources

Find development resources and get your questions answered

View Resources