| ▲ | Show HN: UL-SMF – Open-source linear-complexity ~300x KV-cache compression(github.com) | |
| 13 points by liventruth a day ago | 1 comments | ||
| ▲ | colingauvin a day ago | parent [-] | |
This should be trivially demonstrable if it actually works. Cosine similarity is not a good metric, however, for attention compression. | ||