Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
lxgr
3 months ago
|
parent
|
context
|
favorite
| on:
Serving 70B-scale LLMs efficiently on low-resource...
Even if bandwidth weren't an issue and all users had compatible hardware: You'd still be offloading a (semi-)trusted computation to user hardware, which is usually completely untrusted.
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search: