TensorRT
TensorRT copied to clipboard
pytorch
PyTorch/TorchScript/FX compiler for NVIDIA GPUs using TensorRT
# Description This PR replaces our old shape propagation system which relied on dummy runs of inputs. If the inputs were dynamic, we used to run dummy inference on min,...
# Description Please include a summary of the change and which issue is fixed. Please also include relevant motivation and context. List any dependencies that are required for this change....
## β Question Hello, I've encountered problems installing torch-tensorrt on Windows 10 No matter how I try, how many sources I look up to, there is no clear explanation on...
## Bug Description There is a bug, which I believe for uncompatibility between releases that gives me this error when I try to install the package using the [official documentation](https://pytorch.org/TensorRT/getting_started/installation.html#installation)....
## β Question When I run finetune_qat.py for vgg I get the error: ``` python finetune_qat.py Traceback (most recent call last): File "/home/incar/tms/source/tensortclassicify/finetune_qat.py", line 16, in from pytorch_quantization import nn...
## TL;DR ## Goal(s) ## Tasks ```[tasklist] ### Tasks - [ ] https://github.com/pytorch/TensorRT/issues/2264 - [ ] https://github.com/pytorch/TensorRT/issues/2300 - [ ] https://github.com/pytorch/TensorRT/issues/2308 - [ ] https://github.com/pytorch/TensorRT/issues/2377 - [ ] https://github.com/pytorch/TensorRT/issues/2644 ```...
## Bug Description I used the latest nvidia 23.12 docker image, tried to compile a model with a structure similar to UNET and with pixelshuffle and interpolate operators, set the...
https://github.com/pytorch/TensorRT/blob/5f66adefcea1302e91aa2b3b9e3120636d7027d8/py/torch_tensorrt/dynamo/conversion/converter_utils.py#L273 In this line, if the value is a np.array int, eg, a = np.array(50), then a.shape would be empty, and the `ctx.net.add_constant` function would throw Type error: incompatible function...
## Bug Description Encountered error as follow when using Torch-TensorRT to convert torch.nn.LSTM in docker image nvcr.io/nvidia/pytorch:23.12-py3 :  To Reproduce ## To Reproduce example code: ```python import torch import...
π [Bug] Cannot compile with FP16, "RuntimeError: Expected bias to have type Half but got Float"
## Bug Description I am trying to compile a very simple network with Torch-Tensorrt with FP16. I get the following error message:  ## To Reproduce Steps to reproduce the...
