TensorRT
TensorRT copied to clipboard
PyTorch/TorchScript/FX compiler for NVIDIA GPUs using TensorRT
Adds a "no_conversion" option to torch-tensorrt which when enabled will replace the standard conversion and engine insertion with an embedded function call for each convertible segment. This allows inspection of...
**Is your feature request related to a problem? Please describe.** Would be nice if installing torch-tensorrt just pulled nvidia-tensorrt with it. As well as torchvision when necessary **Describe the solution...
**Is your feature request related to a problem? Please describe.** nvidia-tensorrt is a soft dependency for TS and a hard one for FX. If possible it would be nice to...
**Is your feature request related to a problem? Please describe.** We have this graph: ``` INFO: [Torch-TensorRT] - Segment Block @171: Target: Torch Graph: graph(%1 : bool, %prev_features.1 : Tensor,...
# Description I'm not sure if the issue is with `rules_python` or Bazel but it is not possible to install a Python wheels with Bazel and rules_python if the wheels...
## ❓ Question Currently, I am compiling a custom segmentation model using torch_tensorrt.compile(), using a model script obtained from jit. The code to compile is as follows: ``` scripted_model =...
## ❓ Question **No speed improvement when I use sparse-weights.** I just modified this notebook https://github.com/pytorch/TensorRT/blob/master/notebooks/Hugging-Face-BERT.ipynb And add the sparse_weights=True in the compile part. I also changed the regional bert-base...
## ❓ Question How could I make torchvision.transforms.functional.gaussian_blur operation compatible with torch_tensorrt ? ## What you have already tried Hello. The last step of my forward method is to apply...
Signed-off-by: Bo Wang # Description In some cases, some parameters are graphs' input. We can rewrite them into constants to make sure it works. Fixes #1190 ## Type of change...
## Bug Description FX front-end simple example is broken due to API change. Reported by @jaybdub File /opt/conda/lib/python3.8/site-packages/torch_tensorrt/_compile.py:116, in compile(module, ir, inputs, enabled_precisions, **kwargs) 114 lower_precision = LowerPrecision.FP16 115 elif...