Hasan Arif

icon indicating a website link https://hasanar1f.github.io/ icon indicating an email [email protected]

icon company Virginia Tech icon location Blacksburg, VA, USA icon location AI Researcher Intern at @KaliberAI | PhD Student at Virginia Tech | Ex-MLE at @IQVIA

Results 4 comments of Hasan Arif

what's the difference or advantage of airllm vs flexgen?

and vs DeepSpeed-Inference?

KeyError: 'Cache only has 0 layers, attempted to access layer with index 0'

using transformers==4.33.0 solved it.

KeyError: 'Cache only has 0 layers, attempted to access layer with index 0'

Hi, @Kyriection, as I mentioned, one workaround to avoid this error is to downgrade transformers to something < 3.36. BUT, I am trying to test H2O on some of the...

h2o is slower and not optimized in memory

second that