George S

Hi - to my knowledge, Torch's Dynamo export tracer works slightly differently to `torch.jit.trace`, in that `torch.jit.trace` generally traces only the control flow for the specific input, as you mentioned,...

Hi - thanks for the report - I am able to reproduce the issue. For a quick workaround, try one of the following replacements: ```python pseudo_images = torch.zeros(N, self.side_cells, self.side_cells,...

@HolyWu - thank you very much for this information - this is very helpful. I will take a look at your branch as well

Required for HF model `google/recurrentgemma-2b`

Hi - thank you for the report. Could you also try compiling with the argument `allow_shape_tensors=True`, and share the reported error message, if any? @peri044 - do you have any...

Hi @HolyWu - I wanted to share a few notes on the C++ runtime on Windows after some local testing: - When compiling locally, I had to upgrade the Bazel...

Thanks for the suggestions. I also added `set INCLUDE={TENSORRT_PATH}`, which enabled finding `NvInfer.h`, but now it shows errors for other `.h` files such as the following. I am not sure...

Hi @HolyWu - thanks for the suggestion. Ultimately, the issue was that the repo directory was not its original name, and so the `NvInfer.h` was not included in the `setup.py`....

Hi @HolyWu - ultimately, the issue was my usage of `python setup.py develop` and not `python setup.py bdist_wheel`; the latter works well. I was unable to get around the need...

I have rerun those failing tests - it is also interesting that the accuracy issues on the tests referenced [here](https://github.com/pytorch/TensorRT/pull/2806#issuecomment-2123877884) seem to not have occurred this time.