pytorch/TensorRT
PyTorch/TorchScript/FX compiler for NVIDIA GPUs using TensorRT
This project helps machine learning engineers and MLOps professionals accelerate the inference speed of their PyTorch deep learning models on NVIDIA GPUs. It takes an existing PyTorch model and optimizes it using TensorRT, allowing for significantly faster predictions. The output is an optimized model ready for deployment, either within Python or in a C++ environment.
2,955 stars. Actively maintained with 33 commits in the last 30 days.
Use this if you need to drastically reduce the time it takes for your PyTorch models to make predictions on NVIDIA hardware, especially for real-time applications or high-throughput systems.
Not ideal if your models are not deployed on NVIDIA GPUs, or if you are not working with PyTorch models.
Stars
2,955
Forks
384
Language
Python
License
BSD-3-Clause
Category
Last pushed
Mar 13, 2026
Commits (30d)
33
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/pytorch/TensorRT"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related frameworks
microsoft/onnxruntime
ONNX Runtime: cross-platform, high performance ML inferencing and training accelerator
onnx/onnx
Open standard for machine learning interoperability
PINTO0309/onnx2tf
Self-Created Tools to convert ONNX files (NCHW) to TensorFlow/TFLite/Keras format (NHWC). The...
NVIDIA/TensorRT
NVIDIA® TensorRT™ is an SDK for high-performance deep learning inference on NVIDIA GPUs. This...
onnx/onnxmltools
ONNXMLTools enables conversion of models to ONNX