Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
|
pidtom's submissions
login
1.
Skipping 90% of KV dequant work speeds up LLM decode by 22%
(
github.com/thetom
)
1 point
by
pidtom
40 days ago
|
past
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search:
