.. Torch-TensorRT documentation master file, created by sphinx-quickstart on Mon May 4 13:43:16 2020. You can adapt this file completely to your liking, but it should at least contain the root `toctree` directive. Torch-TensorRT ============== Ahead-of-time compilation of TorchScript / PyTorch JIT for NVIDIA GPUs ----------------------------------------------------------------------- Torch-TensorRT is a compiler for PyTorch/TorchScript, targeting NVIDIA GPUs via NVIDIA's TensorRT Deep Learning Optimizer and Runtime. Unlike PyTorch's Just-In-Time (JIT) compiler, Torch-TensorRT is an Ahead-of-Time (AOT) compiler, meaning that before you deploy your TorchScript code, you go through an explicit compile step to convert a standard TorchScript program into an module targeting a TensorRT engine. Torch-TensorRT operates as a PyTorch extention and compiles modules that integrate into the JIT runtime seamlessly. After compilation using the optimized graph should feel no different than running a TorchScript module. You also have access to TensorRT's suite of configurations at compile time, so you are able to specify operating precision (FP32/FP16/INT8) and other settings for your module. More Information / System Architecture: * `GTC 2020 Talk `_ Getting Started ---------------- * :ref:`installation` * :ref:`getting_started_with_python_api` * :ref:`getting_started_cpp` .. toctree:: :caption: Getting Started :maxdepth: 1 :hidden: getting_started/installation getting_started/getting_started_with_python_api getting_started/getting_started_with_cpp_api getting_started/getting_started_with_windows User Guide ------------ * :ref:`creating_a_ts_mod` * :ref:`getting_started_with_fx` * :ref:`torch_compile` * :ref:`ptq` * :ref:`runtime` * :ref:`saving_models` * :ref:`dynamic_shapes` * :ref:`use_from_pytorch` * :ref:`using_dla` .. toctree:: :caption: User Guide :maxdepth: 1 :hidden: user_guide/creating_torchscript_module_in_python user_guide/getting_started_with_fx_path user_guide/torch_compile user_guide/ptq user_guide/runtime user_guide/saving_models user_guide/dynamic_shapes user_guide/use_from_pytorch user_guide/using_dla Tutorials ------------ * :ref:`torch_tensorrt_tutorials` * :ref:`serving_torch_tensorrt_with_triton` * :ref:`notebooks` .. toctree:: :caption: Tutorials :maxdepth: 3 :hidden: tutorials/serving_torch_tensorrt_with_triton tutorials/notebooks tutorials/_rendered_examples/dynamo/torch_compile_resnet_example tutorials/_rendered_examples/dynamo/torch_compile_transformers_example tutorials/_rendered_examples/dynamo/torch_compile_advanced_usage Python API Documenation ------------------------ * :ref:`torch_tensorrt_py` * :ref:`torch_tensorrt_logging_py` * :ref:`torch_tensorrt_ptq_py` * :ref:`torch_tensorrt_ts_py` * :ref:`torch_tensorrt_fx_py` .. toctree:: :caption: Python API Documenation :maxdepth: 0 :hidden: py_api/torch_tensorrt py_api/logging py_api/ptq py_api/ts py_api/fx C++ API Documenation ---------------------- * :ref:`namespace_torch_tensorrt` * :ref:`namespace_torch_tensorrt__logging` * :ref:`namespace_torch_tensorrt__ptq` * :ref:`namespace_torch_tensorrt__torchscript` .. toctree:: :caption: C++ API Documenation :maxdepth: 1 :hidden: _cpp_api/torch_tensort_cpp _cpp_api/namespace_torch_tensorrt _cpp_api/namespace_torch_tensorrt__logging _cpp_api/namespace_torch_tensorrt__torchscript _cpp_api/namespace_torch_tensorrt__ptq CLI Documentation --------------------- * :ref:`torchtrtc` .. toctree:: :caption: CLI Documenation :maxdepth: 0 :hidden: cli/torchtrtc Contributor Documentation -------------------------------- * :ref:`system_overview` * :ref:`writing_converters` * :ref:`writing_dynamo_aten_lowering_passes` * :ref:`useful_links` .. toctree:: :caption: Contributor Documentation :maxdepth: 1 :hidden: contributors/system_overview contributors/writing_converters contributors/writing_dynamo_aten_lowering_passes contributors/useful_links Indices ---------------- * :ref:`supported_ops` * :ref:`genindex` * :ref:`search` .. toctree:: :caption: Indices :maxdepth: 1 :hidden: indices/supported_ops