tterava

Katago logs most information to stderr. You probably want to output that as well. I'm also using bufsize=0 with my script which works.

Can confirm that TensorRT doesn't work on 5090, except I get a different error: ``` 2025-03-29 10:49:53+0200: Loading model and initializing benchmark... 2025-03-29 10:49:53+0200: Testing with default positions for board...

I tried building katago from source on Windows 11 with Visual Studio 2022, using TensorRT 10.9 and CUDA 12.8 Update 1. I built zlib with: ``` git clone https://github.com/microsoft/vcpkg.git cd...

@gty929 If you're only interested in self play, then you only need zlib1.dll in your Katago folder. If you changed Katago to also use cudart.lib instead of cudart_static.lib (which was...

> For those having RTX5080/5090 GPUs, is TensorRT working now with the default recent KataGo version (such as 1.16.3)? If yes, what is the performance you get please? Performance varies...

Here you go. I used following command to skip most of the low thread counts, and to extend the test a little bit to give more accurate results: katago benchmark...