Michael Feil

@jjmachan It should be now in some versions of langchain.

Hey all, looking forward to contribute this.

Nah, not stale!

I am still waiting for a freaking PR review

@onny Trying to add CLIP here: https://github.com/michaelfeil/infinity/issues/147 -> Is that needed to run the e.g. `laion/CLIP-ViT-B-32-laion2B-s34B-b79K` models?

@thomashacker Ready for review!

@thomashacker Hey Edward, do you have an estimate how long the review takes? Getting hard to remember what I originally submitted as PR by now :)

@thomashacker Yeah, initial review took to long.

@bash99 I think this issue blocks currently: https://github.com/huggingface/optimum/issues/526 You could make it pytorch+cpu compatible. I am not sure if I want to maintain a legacy version of CUDA, I don't...

@talw-nym I hear you, but your point is not clear. Optimum requires torch to be installed, and infinity depends on optimum for onnx inference -> please solve the issue in...