Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
dpflan
on Jan 2, 2023
|
parent
|
context
|
favorite
| on:
Petals: Run 100B+ language models at home bit-torr...
I have not read the technical details, apologies for ignorance, but is there an opportunity for caching?
jerpint
on Jan 2, 2023
[–]
Probably not, since you need to compute the activations of unknown inputs and there could be infinitely many variations of them
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search: