TorchServe v0.7.1 Release Notes

This is the release of TorchServe v0.7.1.

Security

• Upgraded com.google.code.gson:gson from 2.10 to 2.10.1 in serving sdk - #2096 @snyk-bot
• Upgraded ubuntu from 20.04 to rolling in Dockerfile files - #2066, #2065, #2064 @msaroufim
• Update to safe snakeyaml, grpc and gradle - #2081 @jack-gits
  Updated Dockerfile.dev to install gnupg before calling apt-key del 7fa2af80 - #2076 @yeahdongcn

Dependency Upgrades

• Support PyTorch 1.13.1 - #2078 @agunapal

Improvements

• Removed bad eval when onnx session used - #2034 @msaroufim
• Updated runner label in regression_tests_gpu.yml - #2080 @lxning
• Updated nightly benchmark config - #2092 @lxning

Documentation

• Added TorchServe 2022 blogs in Readme - #2060 @msaroufim
  The blogs are Torchserve Performance Tuning, Animated Drawings Case-Study, Walmart Search: Serving Models at a Scale on TorchServe, Scaling inference on CPU with TorchServe, and TorchServe C++ backend.
• Fixed HuggingFace large model instruction - #2087 @HamidShojanazeri
• Reworded examples Readme to highlight examples - #2086 @agunapal
• Updated torchserve_on_win_native.md - #2050 @blackrabbit
• Fixed typo in batch inference md - #2049 @MasoudKaviani

Deprecation

• Deprecated future package and drop Python2 support - #2082 @namannandan

Platform Support

Ubuntu 16.04, Ubuntu 18.04, Ubuntu 20.04 MacOS 10.14+, Windows 10 Pro, Windows Server 2019, Windows subsystem for Linux (Windows Server 2019, WSLv1, Ubuntu 18.0.4). TorchServe now requires Python 3.8 and above, and JDK17.

GPU Support

Torch 1.13 + Cuda 11.7
Torch 1.11 + Cuda 10.2, 11.3, 11.6
Torch 1.9.0 + Cuda 11.1
Torch 1.8.1 + Cuda 9.2