arXiv:2402.02750 — KIVI: A Tuning-Free Asymmetric 2bit Quantization for KV Cache

Fields

id

sources/pap-quant-kivi

URL

https://arxiv.org/abs/2402.02750

Publisher

arXiv

Kind

paper

Published

2024-02-05

Accessed

2026-10-03

notes

arXiv:2402.02750. v1 submitted 2024-02-05. Title on the /abs/ page confirmed as: "KIVI: A Tuning-Free Asymmetric 2bit Quantization for KV Cache". Venue/year for the corresponding paper record come from the Semantic Scholar graph API; see that record's notes where the arXiv comment field or OpenReview was used instead.

Notes

arXiv:2402.02750. v1 submitted 2024-02-05. Title on the /abs/ page confirmed as: "KIVI: A Tuning-Free Asymmetric 2bit Quantization for KV Cache". Venue/year for the corresponding paper record come from the Semantic Scholar graph API; see that record's notes where the arXiv comment field or OpenReview was used instead.

Cross-references

This record references no other records.