Login / Signup
KIVI: A Tuning-Free Asymmetric 2bit Quantization for KV Cache.
Zirui Liu
Jiayi Yuan
Hongye Jin
Shaochen Zhong
Zhaozhuo Xu
Vladimir Braverman
Beidi Chen
Xia Hu
Published in:
CoRR (2024)
Keyphrases
</>
uniform quantization
adaptive quantization
database workloads
prefetching
successive approximation
quantization scheme
quantization error
hash table
main memory
hit rate
transmission line
back end
query processing
electron beam
entropy coding
virtual memory
memory hierarchy
parameter settings
data access