This message was deleted.
# ask-for-help
s
This message was deleted.
c
replied in the other thread, this docs page should help: https://docs.bentoml.org/en/latest/guides/scheduling.html
You are looking for the
workers_per_resource
config
p
ok, got it thanks 🙏
~just for confirmation
workers_per_resource
on GPU mean it’ll copy multiple times same model on GPU, and on CPU mean multithreading right?~
l
Hi Prashant, or you can just left this field, then by default the runner will utilize all cpus in system
1