Chris Vaisnor

> I managed to make it work on my Ubuntu 24.04 system with docker and nvidia-container-toolkit. > > Dockerfile > > ```dockerfile > FROM nvidia/cuda:11.8.0-cudnn8-devel-ubuntu22.04 > > ARG DEBIAN_FRONTEND=noninteractive >...

Checking in here. I am using the Gemini series and token count is populated, but cost is not. Would be super helpful! I looked for where price is queried in...

> [@cvaisnor](https://github.com/cvaisnor) please share more details, ideally sample code but otherwise just models. Are you using pydantic-ai? I would expect the gemini models to work in that case. Here are...

Are you running the main script with cuda enabled? On my AMD Ryzen 9 7950x I get about 3 FPS using all the cores, and when I run it with...

I am running the stream in the default resolution. Using 'face enhancement' with cuda enabled did bring the frames down quite a bit. It runs at around 10FPS now. I'm...

Just tried the above approach. I am trying to get the token cost information working on Logfire for Gemini-2.5-flash. It currently says *UNKNOWN*. However, I noticed that there are two...