SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2408.05646 · 2024

Eigen Attention: Attention in Low-Rank Space for KV Cache Compression

arXiv · PDF · Open in the Atlas

Code that ran

9 of 13 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (0 of them constructed an object rather than computing a result; 3 honoured the contract we drafted, 0 violated it and 1 has no contract verdict; 5 failures of our instrument; 4 no recorded run), measured 2026-11-22; repository links from the Papers with Code archive attributed under CC BY-SA, no affiliation; bodies inline only under a permissive licence as GitHub detects it. Not a reproduction of the paper's results.

"Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results. This record, dated, as JSON: /api/ran/2408.05646.json · badge: /api/ran/2408.05646.svg

Each repository's role is a label: a classifier's output recorded on the link, or, where no role is recorded, what the Papers with Code archive marked. The line under it names its basis. Neither says who wrote the code.

RepositoryRoleRan
utkarshsaxena1/eigenattn canonical (classifier label)
classifier basis: census
9 ran · 4 no recorded run
FunctionStatusWhere it lives
assign_layers_to_gpus Ran
ran on a synthesized input
utkarshsaxena1/eigenattn/parallel_utils.py
pointer only (licence: NONE) · get_code("c29fea147a883771")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, utkarshsaxena1/eigenattn when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

build_mpt_alibi_tensor Ran
ran, honoured the contract we drafted
utkarshsaxena1/eigenattn/models/modelling_mpt_eigen_attn.py
pointer only (licence: NONE) · get_code("6acdafe16c0d4786")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, utkarshsaxena1/eigenattn when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

find_layers Ran
ran; our contract draft was wrong, not the code
utkarshsaxena1/eigenattn/models/models_utils.py
pointer only (licence: NONE) · get_code("904cd61df2fe8fb9")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, utkarshsaxena1/eigenattn when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

get_kvcache_size_opt Ran
ran, honoured the contract we drafted
utkarshsaxena1/eigenattn/main_eigen_attn.py
pointer only (licence: NONE) · get_code("50c5bf862a9fd458")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, utkarshsaxena1/eigenattn when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

get_model_size Ran
ran, honoured the contract we drafted
utkarshsaxena1/eigenattn/main_eigen_attn.py
pointer only (licence: NONE) · get_code("fc00410022bf942a")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, utkarshsaxena1/eigenattn when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

make_disjoint_window Ran
ran; our contract draft was wrong, not the code
utkarshsaxena1/eigenattn/models/models_utils.py
pointer only (licence: NONE) · get_code("4df9168e0a0c38eb")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, utkarshsaxena1/eigenattn when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

parse_eval_args Ran
ran; our contract draft was wrong, not the code
utkarshsaxena1/eigenattn/evaluate_llm.py
pointer only (licence: NONE); the stored copy get_code serves, from BatsResearch/crosslingual-test-time-scaling, is pointer only (licence: NONE) · get_code("400ea4f64ccce5ef")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, utkarshsaxena1/eigenattn when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

sort_layers_by_params Ran
ran; our contract draft was wrong, not the code
utkarshsaxena1/eigenattn/parallel_utils.py
pointer only (licence: NONE) · get_code("aaa7723c864e0a5e")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, utkarshsaxena1/eigenattn when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

truncate_number Ran
ran; our contract draft was wrong, not the code
utkarshsaxena1/eigenattn/models/models_utils.py
pointer only (licence: NONE) · get_code("4e53fbbdfa160f7d")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, utkarshsaxena1/eigenattn when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

get_alpaca Not yet run
unverified (harvested, no recorded run)
utkarshsaxena1/eigenattn/datautils.py
pointer only (licence: NONE) · get_code("131cf84182a40354")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, utkarshsaxena1/eigenattn when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

get_lowest_occupied_gpu Not yet run
unverified (harvested, no recorded run)
utkarshsaxena1/eigenattn/parallel_utils.py
pointer only (licence: NONE) · get_code("3c6439a3c61dd2bb")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, utkarshsaxena1/eigenattn when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

get_pile Not yet run
unverified (harvested, no recorded run)
utkarshsaxena1/eigenattn/datautils.py
pointer only (licence: NONE) · get_code("3b51341ed1a0b73e")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, utkarshsaxena1/eigenattn when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

get_wikitext2 Not yet run
unverified (harvested, no recorded run)
utkarshsaxena1/eigenattn/datautils.py
pointer only (licence: NONE) · get_code("46e078681a1cd741")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, utkarshsaxena1/eigenattn when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

Also present in other papers' code

Of 13 samples lifted from this paper's linked repositories, 13 carry a function identity and 0 do not. Of the 13 distinct functions with an identity, 8 are also present in other papers whose code we hold (8 with at least one paper dated earlier, 0 the same month, 7 later) and 5 are only here among the 52,977 papers whose code Syntology holds (as of 2026-09-26).

Only here means: among the 52,977 papers whose code Syntology holds (51,887 with lifted samples, 1,090 through their assemblies only), as of 2026-09-26, no other paper's lifted samples or current assembly bricks contain an identical function body after normalisation.

FunctionAlso present inEarliest-datedOthers named
parse_eval_args 15 other papers
4 dated earlier, 9 later, 1 same year, order not determinable, 1 undated
2005.14165 (2020-05)
Language Models are Few-Shot Learners
2024.findings-emnlp.86 (2024 (year only))
Tokenization Falling Short: On Subword Robustness in Large Language Models
2405.07938 (2024-05)
EconLogicQA: A Question-Answering Benchmark for Evaluating Large Language Models in Economic Sequential Reasoning
and 12 more not named here
make_disjoint_window 10 other papers
8 dated earlier, 2 later
2304.01089 (2023-04)
RPTQ: Reorder-based Post-training Quantization for Large Language Models
2308.13137 (2023-08)
OmniQuant: Omnidirectionally Calibrated Quantization for Large Language Models
2310.08041 (2023-10)
QLLM: Accurate and Efficient Low-Bitwidth Quantization for Large Language Models
and 7 more not named here
find_layers 9 other papers
8 dated earlier, 1 later
2304.01089 (2023-04)
RPTQ: Reorder-based Post-training Quantization for Large Language Models
2308.13137 (2023-08)
OmniQuant: Omnidirectionally Calibrated Quantization for Large Language Models
2310.08041 (2023-10)
QLLM: Accurate and Efficient Low-Bitwidth Quantization for Large Language Models
and 6 more not named here
truncate_number 8 other papers
7 dated earlier, 1 later
2308.13137 (2023-08)
OmniQuant: Omnidirectionally Calibrated Quantization for Large Language Models
2310.08041 (2023-10)
QLLM: Accurate and Efficient Low-Bitwidth Quantization for Large Language Models
2402.11295 (2024-02)
OneBit: Towards Extremely Low-bit Large Language Models
and 5 more not named here
get_pile 7 other papers
6 dated earlier, 1 later
2308.13137 (2023-08)
OmniQuant: Omnidirectionally Calibrated Quantization for Large Language Models
2310.08041 (2023-10)
QLLM: Accurate and Efficient Low-Bitwidth Quantization for Large Language Models
2402.11295 (2024-02)
OneBit: Towards Extremely Low-bit Large Language Models
and 4 more not named here
get_lowest_occupied_gpu 6 other papers
5 dated earlier, 1 later
2304.01089 (2023-04)
RPTQ: Reorder-based Post-training Quantization for Large Language Models
2308.13137 (2023-08)
OmniQuant: Omnidirectionally Calibrated Quantization for Large Language Models
2310.08041 (2023-10)
QLLM: Accurate and Efficient Low-Bitwidth Quantization for Large Language Models
and 3 more not named here
sort_layers_by_params 6 other papers
5 dated earlier, 1 later
2304.01089 (2023-04)
RPTQ: Reorder-based Post-training Quantization for Large Language Models
2308.13137 (2023-08)
OmniQuant: Omnidirectionally Calibrated Quantization for Large Language Models
2310.08041 (2023-10)
QLLM: Accurate and Efficient Low-Bitwidth Quantization for Large Language Models
and 3 more not named here
build_mpt_alibi_tensor 2 other papers
2 dated earlier
2404.10464 (2024-04)
DESTEIN: Navigating Detoxification of Language Models via Universal Steering Pairs and Head-wise Activation Fusion
2406.02536 (2024-06)
Mitigate Position Bias in Large Language Models via Scaling a Single Dimension

Presence, not direction: an identical function body in two papers' repositories does not say who wrote it, which came from which, or that either paper's method rests on it. Matching is exact after normalisation, so a renamed or edited function is not matched. Dates are when papers appeared, not when code was written. Only .py files the harvester lifted are covered; notebooks are not read. A new-style arXiv id YYMM.NNNN dates a paper to the month 20YY-MM; otherwise Paper.year dates it to the year; otherwise it is undated. Dates are when the paper appeared, not when the code was written. Read 2026-11-22.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Large language models (LLMs) represent a groundbreaking advancement in the domain of natural language processing due to their impressive reasoning abilities. Recently, there has been considerable interest in increasing the context lengths for these models to enhance their applicability to complex tasks. However, at long context lengths and large batch sizes, the key-value (KV) cache, which stores the attention keys and values, emerges as the new bottleneck in memory usage during inference. To address this, we propose Eigen Attention, which performs the attention operation in a low-rank space, thereby reducing the KV cache memory overhead. Our proposed approach is orthogonal to existing KV cache compression techniques and can be used synergistically with them. Through extensive experiments over OPT, MPT, and Llama model families, we demonstrate that Eigen Attention results in up to 40% reduction in KV cache sizes and up to 60% reduction in attention operation latency with minimal drop in performance. Code is available at https://github.com/UtkarshSaxena1/EigenAttn.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2408.05646")
get_code_for_paper("2408.05646")
have("2408.05646")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2408.05646.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2408.05646.svg)](https://syntology.ai/paper/2408.05646)

Connect an agent — have() is free.