lachlancahill
lachlancahill
I have the same issue. ffmpeg is already installed. Since no error is raised it's hard to diagnose.
Wondering if there is any update on this? Edge weights would be an incredible addition to Node2Vec.
> FWIW I get like 95+% utilization when running inference on Mac Metal (specifically using Mistral-7b, used via repeated ollama REST API queries). > > Speculating, I feel like this...
> Your parallelization should be done under GPU-level, not system-level. The GPU is blocked until it finishes each inference. You should change the guidance function in a manner that it...
> @lachlancahill Were you able to find this out? Not with this library, but the [outlines](https://github.com/outlines-dev/outlines) library does support batch inference and I am seeing great results with it. I...