Yan Ma

@masaldana2 a quick fix of this is sitting on swift-fix branch!

Retry did work for all the chains in the llama local notebook, except for this line: ``` # Compile app = workflow.compile() # Test from pprint import pprint inputs =...

I can certainly generate a pull request from my fork.

Any idea what the minimum model would be required?

I found that point it at my keyboard for initialization helps, but yeah the default setting seems to lose track quite often. I'm using a pseye calibrated with ATAN model....

Curious about this as well. Struggling to train a scene on a 8GB graphics card without running into memory allocation failure. Just wondering what are the knobs we can play...

> Curious about this as well. Struggling to train a scene on a 8GB graphics card without running into memory allocation failure. Just wondering what are the knobs we can...

Actually, the subscriber seems to be working, while the publisher doesn't.