This seems extremely inefficient considering data transfer between model layers if the model is distributed. I found this project called Petals that claim up to 4 tok/s for a 180B model although its repository hasn't been updated in two years.
https://petals.dev/
For prompt processing it would work though, and it could for diffusion LLMs as well.
reply
This seems extremely inefficient considering data transfer between model layers if the model is distributed. I found this project called Petals that claim up to 4 tok/s for a 180B model although its repository hasn't been updated in two years.
https://petals.dev/