Knowledge Graph

Graph explorer

Search resolved entities, walk their edges, and read the sentence behind every one.

Entities25 of 207,987

Entity

KVQuant

technology1 mentionslast seen Sep 16, 2026

An existing KV quantization method that keeps sparse full-precision outliers that a dense array cannot hold in place.

Relationships 1

key-value cache quantizationsupersedesKVQuant70% confidence1 source

Relationship

key-value cache quantizationsupersedesKVQuant

70% confidence1 supporting mentions

Either name opens that entity’s relationships.

Sources 1

preprintarXivSep 4, 2026Interface-Aware KV Cache Quantization for Dense On-Chip NVM in Long-Context LLM Decoding
KIVI attaches per-group metadata, adding about 25% to the stored KV cache; KVQuant keeps sparse full-precision outliers that a dense array cannot hold in place. This paper examines what these structures cost when the KV cache resides in NVM behind fixed-range converters, and designs a quantization scheme matched to that interface.