Tripy: A Python Programming Model For TensorRT

Quick Start | Installation | Examples | Notebooks | Contributing | Documentation

Tripy is a debuggable, Pythonic frontend for TensorRT, a deep learning inference compiler.

What you can expect:

• High performance by leveraging TensorRT's optimization capabilties.
• An intuitive API that follows conventions of the ecosystem.
• Debuggability with features like eager mode to interactively debug mistakes.
• Excellent error messages that are informative and actionable.
• Friendly documentation that is comprehensive but concise, with code examples.

Quick Start

See the Introduction To Tripy guide for details:

• Defining a model:

  class Model(tp.Module):
      def __init__(self):
          self.conv = tp.Conv(in_channels=1, out_channels=1, kernel_dims=[3, 3])
  
      def __call__(self, x):
          x = self.conv(x)
          x = tp.relu(x)
          return x
  

• Initializing it:

  model = Model()
  model.load_state_dict(
      {
          "conv.weight": tp.ones((1, 1, 3, 3)),
          "conv.bias": tp.ones((1,)),
      }
  )
  
  dummy_input = tp.ones((1, 1, 4, 4))
  

• Executing in eager mode:

  eager_out = model(dummy_input)
  

• Compiling and executing:

  compiled_model = tp.compile(
      model,
      args=[tp.InputInfo(shape=(1, 1, 4, 4), dtype=tp.float32)],
  )
  
  compiled_out = compiled_model(dummy_input)
  

Installation

Installing Prebuilt Wheels

python3 -m pip install nvtripy -f https://nvidia.github.io/TensorRT-Incubator/packages.html

Building Wheels From Source

For the latest changes, build Tripy wheels from source:

1. Install build:

   python3 -m pip install build
   

2. Build a wheel from the tripy root directory:

   python3 -m build . -w
   

3. Install the wheel from the tripy root directory:

   python3 -m pip install -f https://nvidia.github.io/TensorRT-Incubator/packages.html dist/nvtripy-*.whl
   

4. [Optional] Sanity check:

   python3 -c "import nvtripy as tp; x = tp.ones((5,), dtype=tp.int32); assert x.tolist() == [1] * 5"