Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
JackYoustra
8 months ago
|
parent
|
context
|
favorite
| on:
The Llama 4 herd
Standard Transformer KV caches are empirically quite sparse. I wonder if they've made some fix along those lines
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search:
