Papers › CSKV: Training-Efficient Channel Shrinking for KV Cache in Long-Context Scenarios

CSKV: Training-Efficient Channel Shrinking for KV Cache in Long-Context Scenarios

16 Sep 2024arXiv:2409.10593archive 2025-07-28

Luning Wang, Shiyao Li, Xuefei Ning, Zhihang Yuan, Shengen Yan, Guohao Dai, Yu Wang

Large Language Models (LLMs) have been widely adopted to process long-context tasks. However, the large memory overhead of the key-value (KV) cache poses significant challenges in long-context scenarios. Existing training-free KV cache compression methods typically focus on quantization and token pruning, which have compression limits, and excessive sparsity can lead to severe performance degradation. Other methods design new architectures with less KV overhead but require significant training overhead. To address the above two drawbacks, we further explore the redundancy in the channel dimension and apply an architecture-level design with minor training costs. Therefore, we introduce CSKV, a training-efficient Channel Shrinking technique for KV cache compression: (1) We first analyze the singular value distribution of the KV cache, revealing significant redundancy and compression potential along the channel dimension. Based on this observation, we propose using low-rank decomposition for key and value layers and storing the low-dimension features. (2) To preserve model performance, we introduce a bi-branch KV cache, including a window-based full-precision KV cache and a low-precision compressed KV cache. (3) To reduce the training costs, we minimize the layer-wise reconstruction loss for the compressed KV cache instead of retraining the entire LLMs. Extensive experiments show that CSKV can reduce the memory overhead of the KV cache by 80% while maintaining the model's long-context capability. Moreover, we show that our method can be seamlessly combined with quantization to further reduce the memory overhead, achieving a compression ratio of up to 95%. Code is available at https://github.com/wln20/CSKV.

PaperPDFCodeCode Syntology ran

In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.

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

For agents, on Syntology's MCP service (how to connect):

Code

Syntology 9 code samples harvested from 1 repository linked to this paper: 4 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 1 where Syntology's instrument failed) · 5 unverified. Where Syntology's instrument failed: 1 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: official repository: 9 samples from 1 repository, 4 ran (3 with no instrument failure; 1 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

Levels written on 2026-09-24 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

wln20/CSKV officialmentioned in papermentioned on GitHubpytorchSyntology: 9 samples, 4 ran (1 instrument-failed) · 5 unverified 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

9 samples harvested: 4 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 1 where Syntology's instrument failed) · 5 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

1ran · our draft was wrong
3ran
5unverified

Licence: 9 of the 9 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 wln20/CSKV. “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. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (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 are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. 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 six 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; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. 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.

A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity.

wln20/CSKV official repository 9 samples, 4 ran (1 instrument-failed) · 5 unverified
forward_mistral cskv_src/modeling/modeling_mistral.py ran no licence file found · pointer only · 53c019a2f72f6891 · report fixture: signature self:callable/0/?, input_ids:Tensor/2/int, attention_mask:Tensor/2/int, position_ids:Tensor/2/int, past_key_values:NoneType/0/?, inputs_embeds:NoneType/0/?, labels:Tensor/2/int, use_cache:bool/0/bool, output_attentions:bool/0/bool, output_hidden_states:bool/0/bool, return_dict:bool/0/bool · returned CausalLMOutputWithPast · level recorded 2026-09-24
get_name in 20 papers cskv_src/utils/general_utils.py ran · our draft was wrong no licence file found · pointer only · 8717d7f11f169bd2 · report fixture: signature args:Args/0/? · returned str · level recorded 2026-09-24
init_svd cskv_src/utils/training_utils.py ran no licence file found · pointer only · b11f68f08e771fbd · report fixture: signature proj_weight:Tensor/2/float, compressed_dim_per_head:int/0/int, num_heads:int/0/int · returned tuple · level recorded 2026-09-24
init_svd_parallel_inference cskv_src/utils/training_utils.py ran no licence file found · pointer only · fb2320a6cd6c2461 · report fixture: signature proj_weight:Tensor/2/float, compressed_dim_per_head:int/0/int, num_heads:int/0/int · returned tuple · level recorded 2026-09-24
get_dataset_for_calib cskv_src/utils/data_utils.py unverified no licence file found · pointer only · 99c1c2ed2f9a3ae0 · report
get_dataset_for_trainer cskv_src/utils/data_utils.py unverified no licence file found · pointer only · 6dd2377be358412b · report
init_asvd cskv_src/utils/training_utils.py unverified no licence file found · pointer only · 607710bbee79e7ac · report
prepare_inputs_for_generation_llama cskv_src/modeling/modeling_llama.py unverified no licence file found · pointer only · 90861e147e3c2c04 · report
prepare_inputs_for_generation_mistral cskv_src/modeling/modeling_mistral.py unverified no licence file found · pointer only · 3472698614a9b449 · report

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Focus

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