Papers › ZipCache: Accurate and Efficient KV Cache Quantization with Salient Token Identification

ZipCache: Accurate and Efficient KV Cache Quantization with Salient Token Identification

23 May 2024arXiv:2405.14256archive 2025-07-28

Yefei He, Luoming Zhang, Weijia Wu, Jing Liu, Hong Zhou, Bohan Zhuang

KV cache stores key and value states from previous tokens to avoid re-computation, yet it demands substantial storage space, especially for long sequences. Adaptive KV cache compression seeks to discern the saliency of tokens, preserving vital information while aggressively compressing those of less importance. However, previous methods of this approach exhibit significant performance degradation at high compression ratios due to inaccuracies in identifying salient tokens. In this paper, we present ZipCache, an accurate and efficient KV cache quantization method for LLMs. First, we construct a strong baseline for quantizing KV cache. Through the proposed channel-separable tokenwise quantization scheme, the memory overhead of quantization parameters are substantially reduced compared to fine-grained groupwise quantization. To enhance the compression ratio, we propose normalized attention score as an effective metric for identifying salient tokens by considering the lower triangle characteristics of the attention matrix. Moreover, we develop an efficient approximation method that decouples the saliency metric from full attention scores, enabling compatibility with fast attention implementations like FlashAttention. Extensive experiments demonstrate that ZipCache achieves superior compression ratios, fast generation speed and minimal performance losses compared with previous KV cache compression methods. For instance, when evaluating Mistral-7B model on GSM8k dataset, ZipCache is capable of compressing the KV cache by 4.98×, with only a 0.38% drop in accuracy. In terms of efficiency, ZipCache also showcases a 37.3% reduction in prefill-phase latency, a 56.9% reduction in decoding-phase latency, and a 19.8% reduction in GPU memory usage when evaluating LLaMA3-8B model with a input length of $4096$.

PaperPDFCodeCode Syntology ran

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="2405.14256")

Code

Syntology Ran 3 of 6 code samples harvested from 1 repository linked to this paper; 3 have no recorded run. Of those that ran: 1 ran · our draft was wrong; 2 ran · fixture could not drive it.

By repository: community (archive-listed): 6 samples from 1 repository, 3 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

thisisbillhe/zipcache mentioned on GitHubpytorchMIT report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

6 samples harvested; 3 ran; 0 honoured the contract we drafted; 3 have no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

1ran · our draft was wrong
2ran · fixture could not drive it
3unverified

Licence: 0 of the 6 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from thisisbillhe/zipcache. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples from a repository marked official are listed first. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of four reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

repeat_kv thisisbillhe/zipcache/zipcache/models/modeling_llama.py community (archive-listed) ran · fixture could not drive it fingerprinted MIT (permissive) · 30d7eec482ebf6b1 · report
apply_rotary_pos_emb thisisbillhe/zipcache/zipcache/models/modeling_llama.py community (archive-listed) ran · fixture could not drive it MIT (permissive) · d61c483a3c2b3156 · report
rotate_half thisisbillhe/zipcache/zipcache/models/modeling_llama.py community (archive-listed) ran · our draft was wrong fingerprinted MIT (permissive) · b99eea6376d1e212 · report
transfer_2bit_to_8bit_batchwise thisisbillhe/zipcache/zipcache/models/CompressUtils/compress_function.py community (archive-listed) unverified MIT (permissive) · b167b70daca2e13d · report
transfer_8bit_to_2bit_batchwise thisisbillhe/zipcache/zipcache/models/CompressUtils/compress_function.py community (archive-listed) unverified MIT (permissive) · 8e36b8276cd96cd4 · report
transfer_8bit_to_4bit thisisbillhe/zipcache/zipcache/models/CompressUtils/compress_function.py community (archive-listed) unverified MIT (permissive) · 3b8503ce511cc73c · report

Tasks

GSM8KQuantization

1 archive task tag without a task page not shown.

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

SPEED

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections