Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
HPsquared
6 months ago
|
parent
|
context
|
favorite
| on:
Show HN: Speeding up LLM inference 2x times (possi...
Halfweight. Half the weights, half the wait, half the wit.
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search:
