Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
eli
38 days ago
|
parent
|
context
|
favorite
| on:
Nvidia Nemotron 3.5 Lightning and NeMo Switchyard
I've seen ones that are configurable to pick a trade off point between lower cost (cache stickiness) and routing performance (best model for that turn).
But yeah I'm skeptical all this overhead is worth it.
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search:
But yeah I'm skeptical all this overhead is worth it.