//
sign in
Post
by @danabra.mov
PostEmbed
by @danabra.mov
Record
by @jimpick.com
Record
by @atsui.org
+ new component
Post
⚖️ The magic works only if accuracy is preserved even at high compression ratios. Enter Dynamic Memory Sparsification (DMS), which achieves 8x KV cache compression with 1K training steps and retains accuracy better than SOTA methods.
Jun 6, 2025
Edoardo Ponti