Skip to content

Latest commit

 

History

History
36 lines (29 loc) · 2.32 KB

CONTRIBUTING.md

File metadata and controls

36 lines (29 loc) · 2.32 KB
Raw

Contributing to TorchServe

If you are interested in contributing to TorchServe, your contributions will fall into two categories:

  1. You want to propose a new feature and implement it.
    • Post about your intended feature as an issue, and we will discuss the design and implementation. Once we agree that the plan looks good, go ahead and implement it.
  2. You want to implement a feature or bug-fix for an outstanding issue.

    • Search for your issue here: https://github.com/pytorch/serve/issues

    • Pick an issue and comment on the task that you want to work on this feature.

    • To ensure your changes doesn't break any of the existing features run the sanity suite as follows from serve directory:

      • Install dependencies (if not already installed) For CPU

        python ts_scripts/install_dependencies.py --environment=dev

      For GPU bash python ts_scripts/install_dependencies.py --environment=dev --cuda=cu102 > Supported cuda versions as cu111, cu102, cu101, cu92

      • Run sanity suite 
        python torchserve_sanity.py

    • Run Regression test python test/regression_tests.py

    • For running individual test suites refer code_coverage documentation

    • If you are updating an existing model make sure that performance hasn't degraded by running benchmarks on the master branch and your branch and verify there is no performance regression

    • For large changes make sure to run the automated benchmark suite which will run the apache bench tests on several configurations of CUDA and EC2 instances

    • If you need more context on a particular issue, please create raise a ticket on TorchServe GH repo or connect to PyTorch's slack channel

Once you finish implementing a feature or bug-fix, please send a Pull Request to https://github.com/pytorch/serve. Use this template when creating a Pull Request.

For more non-technical guidance about how to contribute to PyTorch, see the Contributing Guide.