Yule Hou
Yule Hou
TensorRT 8.5.0 is not yet released and I can see driver version mismatch in your setup. Please refer to [this](https://docs.nvidia.com/deeplearning/tensorrt/support-matrix/index.html) for platform compatibility. Nevertheless, I had planned to submit patches...
Thanks to your very detailed reproduce instructions, I was able to reproduce the issue. With `DEBUG_INTERMEDIATE_VALUES`, it turns out that the 3rd block of trunk got all of nans as...
> Thanks to your very detailed reproduce instructions, I was able to reproduce the issue. With `DEBUG_INTERMEDIATE_VALUES`, it turns out that the 3rd block of trunk got all of nans...
x86也许除外。
> About TensorRT > > * Below is the debug log for TensorRT-8.5.2.2.Windows10.x86_64.cuda-11.8.cudnn8.6. > * cuda, cudnn dlls are used from nvinfer_builder_resource.dll. > > ``` > 'katago.exe' (Win32): 'katago.exe' was...
The upstream issue has been fixed in transitive-bullshit/chatgpt-api#425.
The issue was fixed in transitive-bullshit/chatgpt-api#425.
> Hi, I'm a little bit curious why the plan cache became 30x smaller, I refer to the doc, it seems that refitter is used to change engine weight dynamically....
> Thanks for your work. I ran into a problem when compile it with TensorRT 10.1.0 . The CMakeLists.txt cannot read version number in NvInferVersion.h since it changed the encoding...