NQKV is a block-wise 4-bit KV cache quantizer that uses a normal-distribution lookup table to let OPT models run with larger batches or longer contexts at negligible measured accuracy cost.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
NQKV: A KV Cache Quantization Scheme Based on Normal Distribution Characteristics
NQKV is a block-wise 4-bit KV cache quantizer that uses a normal-distribution lookup table to let OPT models run with larger batches or longer contexts at negligible measured accuracy cost.