Papers › KV Cache Compression, But What Must We Give in Return? A Comprehensive Benchmark of...

KV Cache Compression, But What Must We Give in Return? A Comprehensive Benchmark of Long Context Capable Approaches

1 Jul 2024arXiv:2407.01527archive 2025-07-28

Jiayi Yuan, Hongyi Liu, Shaochen Zhong, Yu-Neng Chuang, Songchen Li, Guanchu Wang, Duy Le, Hongye Jin, Vipin Chaudhary, Zhaozhuo Xu, Zirui Liu, Xia Hu

Long context capability is a crucial competency for large language models (LLMs) as it mitigates the human struggle to digest long-form texts. This capability enables complex task-solving scenarios such as book summarization, code assistance, and many more tasks that are traditionally manpower-intensive. However, transformer-based LLMs face significant challenges with long context input due to the growing size of the KV cache and the intrinsic complexity of attending to extended inputs; where multiple schools of efficiency-driven approaches - such as KV cache quantization, token dropping, prompt compression, linear-time sequence models, and hybrid architectures - have been proposed to produce efficient yet long context-capable models. Despite these advancements, no existing work has comprehensively benchmarked these methods in a reasonably aligned environment. In this work, we fill this gap by providing a taxonomy of current methods and evaluating 10+ state-of-the-art approaches across seven categories of long context tasks. Our work reveals numerous previously unknown phenomena and offers insights - as well as a friendly workbench - for the future development of long context-capable LLMs. The source code is available at https://github.com/henryzhongsc/longctx_bench.

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="2407.01527")

Code

Syntology Ran 12 of 13 code samples harvested from 1 repository linked to this paper; 1 has no recorded run. Of those that ran: 1 ran · honoured contract; 2 ran · our draft was wrong; 9 ran with no contract checked.

By repository: official repository: 13 samples from 1 repository, 12 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

henryzhongsc/longctx_bench officialmentioned in papermentioned 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

13 samples harvested; 12 ran; 1 honoured the contract we drafted; 1 has 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 · honoured contract
2ran · our draft was wrong
9ran
1unverified

Licence: 0 of the 13 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 henryzhongsc/longctx_bench. “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.

build_chat henryzhongsc/longctx_bench/pipeline/model_utils.py official repository ran MIT (permissive) · 3b19a66bec30b1b9 · report
count_score henryzhongsc/longctx_bench/eval/longbench_utils/metrics.py official repository ran · honoured contract fingerprinted MIT (permissive) · b349b79d9cc2934b · report
count_words henryzhongsc/longctx_bench/eval/passkey_utils/passkey_utils.py official repository ran fingerprinted MIT (permissive) · 2207706bbe348d2c · report
distraction_allowed_partial_match henryzhongsc/longctx_bench/eval/passkey_utils/eval_metrics.py official repository ran MIT (permissive) · ecac1fc997b729b6 · report
eval_by_metric henryzhongsc/longctx_bench/eval/passkey_utils/eval_metrics.py official repository ran MIT (permissive) · 01c26d6cb82784d2 · report
get_intermediate_values_within_min_max henryzhongsc/longctx_bench/eval/passkey_utils/passkey_utils.py official repository ran MIT (permissive) · 932a134ef3a83a86 · report
load_data henryzhongsc/longctx_bench/eval/longbench_utils/eval_long_bench.py official repository ran MIT (permissive) · 4d685bf704394edd · report
normalize_answer henryzhongsc/longctx_bench/eval/longbench_utils/metrics.py official repository ran · our draft was wrong fingerprinted MIT (permissive) · e7e75981cb464788 · report
normalize_answer henryzhongsc/longctx_bench/eval/passkey_utils/eval_metrics.py official repository ran fingerprinted MIT (permissive) · 92035fa2c8ef3cbe · report
normalize_zh_answer henryzhongsc/longctx_bench/eval/longbench_utils/metrics.py official repository ran · our draft was wrong fingerprinted MIT (permissive) · 8c5c581f9264c810 · report
register_args_and_configs henryzhongsc/longctx_bench/pipeline/main_utils.py official repository ran MIT (permissive) · 682b08abcc125f52 · report
truncate_string_by_word_count henryzhongsc/longctx_bench/eval/passkey_utils/passkey_utils.py official repository ran MIT (permissive) · 319e766d2cafe502 · report
set_logger henryzhongsc/longctx_bench/pipeline/main_utils.py official repository unverified MIT (permissive) · d86a7d51ce10c6e4 · report

Tasks

Quantization

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.

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