Y
Hacker News
new
|
ask
|
show
|
jobs
by
Gracana
85 days ago
ktransformers can do dynamic placement of experts and could presumably produce such a histogram, though currently its activation statistics are just a ".pt" file.
https://github.com/kvcache-ai/ktransformers/blob/main/doc/en...
FWIW I never got it to work and did not dig into it much.