mila

Tag

Cards List
#mila

@VukRosic99: Most KV-cache compression applies SVD to the keys alone, or embeds queries and keys jointly. Both miss the obvious targ…

X AI KOLs Timeline · 2026-07-10 Cached

KQ-SVD is a new method for KV-cache compression that directly approximates the attention matrix via optimal low-rank decomposition, achieving 5-10x lower error than key-only SVD on LLaMA and Mistral models.

0 favorites 0 likes
← Back to home

Submit Feedback