Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
Show HN: UL-SMF – Open-source linear-complexity ~300x KV-cache compression
(
github.com/liventruth
)
13 points
by
liventruth
16 days ago
|
hide
|
past
|
favorite
|
1 comment
colingauvin
15 days ago
|
next
[–]
This should be trivially demonstrable if it actually works. Cosine similarity is not a good metric, however, for attention compression.
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search: