SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2407.11550 · NeurIPS · 2025

Ada-KV: Optimizing KV Cache Eviction by Adaptive Budget Allocation for Efficient LLM Inference

S Zhou, Yuan Feng, Junlin Lv, Yukun Cao, Xike Xie

arXiv · PDF · Open in the Atlas

Code that ran

1 of 5 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; 0 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 1 failure 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/2407.11550.json · badge: /api/ran/2407.11550.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
FFY0/AdaKV canonical (classifier label)
classifier basis: classifier_2025
1 ran · 0 no recorded run
NVIDIA/kvpress marked official in Papers with Code
Papers with Code archive
0 ran · 3 no recorded run
ffy0/adakv community
Papers with Code archive
0 ran · 1 no recorded run
FunctionStatusWhere it lives
config_compress Ran
ran; our contract draft was wrong, not the code
FFY0/AdaKV/adaptive_snapkv/monkeypatch/monkeypatch.py
pointer only (licence: NOASSERTION) · get_code("2cc48d857fba9681")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, FFY0/AdaKV (NOASSERTION). 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.

AdaKVPress Not yet run
unverified (harvested, no recorded run)
NVIDIA/kvpress/kvpress/presses/adakv_press.py
code served (permissive licence) · get_code("4fae14db255bbbe6")
How it ran

no invocation recorded.

AdaptiveSnapKVCluster Not yet run
unverified (harvested, no recorded run)
ffy0/adakv/adaptive_snapkv/monkeypatch/snapkv_utils.py
pointer only (licence: NOASSERTION) · get_code("016e62e773c90c11")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, ffy0/adakv (NOASSERTION). 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.

BasePress Not yet run
unverified (harvested, no recorded run)
NVIDIA/kvpress/kvpress/presses/adakv_press.py
code served (permissive licence) · get_code("c4f6af4dd0288d5c")
How it ran

no invocation recorded.

ScorerPress Not yet run
unverified (harvested, no recorded run)
NVIDIA/kvpress/kvpress/presses/adakv_press.py
code served (permissive licence) · get_code("1fa519d26ac61a5b")
How it ran

no invocation recorded.

Also present in other papers' code

Of 5 samples lifted from this paper's linked repositories, 5 carry a function identity and 0 do not. Of the 5 distinct functions with an identity, 2 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 2 later) and 3 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
BasePress
brick of this paper's assembly: helper
2 other papers
2 later
2502.03805 (2025-02)
CriticalKV: Optimizing KV Cache Eviction from an Output Perturbation Perspective
2608.19920 (2026-08)
Learning how to Forget: Fine-tuning for Long-Context Sparse Attention
ScorerPress
brick of this paper's assembly: helper
2 other papers
2 later
2502.03805 (2025-02)
CriticalKV: Optimizing KV Cache Eviction from an Output Perturbation Perspective
2608.19920 (2026-08)
Learning how to Forget: Fine-tuning for Long-Context Sparse Attention

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 have excelled in various domains but face efficiency challenges due to the growing Key-Value (KV) cache required for long-sequence inference. Recent efforts aim to reduce KV cache size by evicting vast non-critical cache elements during runtime while preserving generation quality. However, these methods typically allocate compression budgets uniformly across all attention heads, ignoring the unique attention patterns of each head. In this paper, we establish a theoretical loss upper bound between pre-and post-eviction attention output, explaining the optimization target of prior cache eviction methods, while guiding the optimization of adaptive budget allocation. Base on this, we propose Ada-KV, the first head-wise adaptive budget allocation strategy. It offers plug-and-play benefits, enabling seamless integration with prior cache eviction methods. Extensive evaluations on 13 datasets from Ruler and 16 datasets from LongBench, all conducted under both question-aware and question-agnostic scenarios, demonstrate substantial quality improvements over existing methods. Our code is available at https://github.com/FFY0/AdaKV.

For agents

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

get_harvested_code_for_paper("2407.11550")
get_code_for_paper("2407.11550")
have("2407.11550")

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

curl https://syntology.ai/api/ran/2407.11550.json

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

[![Syntology run record](https://syntology.ai/api/ran/2407.11550.svg)](https://syntology.ai/paper/2407.11550)

Connect an agent — have() is free.