Aaron Pham

What is the resource you are running on?

i can successfully run opt without any hiccups on mac. OPT shouldn't require GPU to run at all

seems like your machine doesn't have enough resource, hence they are offloading it to disk. I will need more bandwidth to investigate how to run falcon on smaller machine

Please reopen if you still see this error on 0.3.0

see #87 for fixes

Will release a patch soon

Hey there, we discussed internally about more extensive custom path support, and want to share the decision: With custom model path, it is best that when you do o`penllm start...

WIP on https://github.com/bentoml/OpenLLM/pull/102

Please try out 0.1.20

can you send the full traceback here?