Hacker Newsnew | past | comments | ask | show | jobs | submitlogin
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


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: