Triton Model Navigator v0.5.0

• new: Support for PyTriton deployemnt

• new: Support for Python models with python.optimize API

• new: PyTorch 2 compile CPU and CUDA runners

• new: Collect conversion max batch size in status

• new: PyTorch runners with compile support

• change: Improved handling CUDA and CPU runners

• change: Reduced finding device max batch size time by running it once as separate pipeline

• change: Stored find max batch size result in separate filed in status

• Version of external components used during testing:

  • PyTorch 1.14.0a0+410ce96
  • TensorFlow 2.11.0
  • TensorRT 8.5.3
  • ONNX Runtime 1.13.1
  • Polygraphy: 0.44.2
  • GraphSurgeon: 0.4.6
  • tf2onnx v1.13.0
  • Other component versions depend on the used framework containers versions.
    See its support matrix
    for a detailed summary.