method · first seen 7 Oct 2026
KV cache pruning
Reducing key-value cache reads by dropping or skipping less important channels or tokens during decoding.
Mentions per week
PapersCodeDiscussion
Earliest sources
- Dual-QK: Sharp Queries and Flat Keys for Prunable 2-bit KV CachesPapers · 7 Oct 2026 · Sunjoo Whang, Jungjun Oh, Minsung Kim, Dongho Seo, Jisu Shin, Gregory Kielian, H…
Latest sources
- Dual-QK: Sharp Queries and Flat Keys for Prunable 2-bit KV CachesPapers · 7 Oct 2026 · Sunjoo Whang, Jungjun Oh, Minsung Kim, Dongho Seo, Jisu Shin, Gregory Kielian, H…