TensorRT
TensorRT copied to clipboard
PyTorch/TorchScript/FX compiler for NVIDIA GPUs using TensorRT
# Description Small changes to address outstanding issues Fixes #266 Fixes #834 ## Type of change Please delete options that are not relevant and/or add your own. - Bug fix...
## Bug Description I try to convert yolov5-face torch model (more specifically yolov5n-0.5.pt) to TensorRT embedded torchscript model with your repo. The JIT model works correctly and there is no...
## Bug Description ```html ERROR: [Torch-TensorRT] - Method requested cannot be compiled by Torch-TensorRT.TorchScript. Unsupported operators listed below: - aten::cross_entropy_loss(Tensor self, Tensor target, Tensor? weight=None, int reduction=1, int ignore_index=-100, float...
## ❓ Question Let's assume one converts a TorchScript to a Torch-TensorRT TorchScript requesting inference type to be FP16. At conversion time, if the GPU doesn't support FP16 (GTX1060 typically),...
## Bug Description TensorRT fails to export PyTorch transformer encoder. Same is true for PyTorch transformer decoder, failing with the same error. ## To Reproduce Steps to reproduce the behavior:...
## Bug Description I get RuntimeError when I try to save a compiled Tensor RT module. The error message says to report a bug, and I found no other issues...
## ❓ Question I'm trying to install `torch-tensorrt` on a Jetson AGX Xavier. I first installed `pytorch` 1.12.0 and `torchvision` 0.13.0 following this [guide](https://forums.developer.nvidia.com/t/pytorch-for-jetson-version-1-11-now-available/72048). Then I installed `torch-tensorrt` following this...
I try to use python trtorch==0.4.1 to compile my own pytorch jit traced model, and I find that it goes wrong with the following information: ` Traceback (most recent call...
## Bug Description Returning a list of tensors fails when ops are applied to the tensors prior to appending them to the list that is returned. This is not the...
## ❓ Question Is there support for optional arguments in model's `forward()`? For example, I have the following: `def forward(self, x, y: Optional[Tensor] = None):` where `y` is an optional...