SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2406.13474 · ICML · 2025

BOA: Attention-aware Post-training Quantization without Backpropagation

Yongkweon Jeon, Joonyoung Kim, Junhan Kim, Chungman Lee, Eulrang Cho, Ho-Young Kim

arXiv · PDF · Open in the Atlas

Code that ran

10 of 11 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (1 of them constructed an object rather than computing a result; 0 honoured the contract we drafted, 0 violated it and 1 has no contract verdict; 9 failures of our instrument; 1 no recorded run), measured 2026-11-22; 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/2406.13474.json · badge: /api/ran/2406.13474.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
SamsungLabs/BoA community
Papers with Code archive
10 ran · 1 no recorded run
FunctionStatusWhere it lives
BoA Ran
ran on a synthesized input · constructed an object; no result was computed
SamsungLabs/BoA/quantizers/boa.py
pointer only (licence: NOASSERTION) · get_code("30794ea4f77e617d")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, SamsungLabs/BoA (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.

damping Ran
ran; our contract draft was wrong, not the code
SamsungLabs/BoA/quantizers/boa.py
pointer only (licence: NOASSERTION) · get_code("f454b164e03e97cd")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, SamsungLabs/BoA (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.

fake_quantize Ran
ran; our contract draft was wrong, not the code
SamsungLabs/BoA/quantizers/boa.py
pointer only (licence: NOASSERTION) · get_code("e720961192f8cc13")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, SamsungLabs/BoA (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.

filter_dead_neuron Ran
ran; our contract draft was wrong, not the code
SamsungLabs/BoA/quantizers/boa.py
pointer only (licence: NOASSERTION) · get_code("e7cdd0d8ff38c485")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, SamsungLabs/BoA (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.

get_cholesky_of_inverse Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
SamsungLabs/BoA/quantizers/boa.py
pointer only (licence: NOASSERTION) · get_code("b4ee4d03c2667d47")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, SamsungLabs/BoA (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.

quantize Ran
ran; our contract draft was wrong, not the code
SamsungLabs/BoA/quantizers/boa.py
pointer only (licence: NOASSERTION) · get_code("b6a41484b3b9b656")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, SamsungLabs/BoA (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.

reorder_col Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
SamsungLabs/BoA/quantizers/boa.py
pointer only (licence: NOASSERTION) · get_code("43c717cebadf7e91")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, SamsungLabs/BoA (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.

reorder_row Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
SamsungLabs/BoA/quantizers/boa.py
pointer only (licence: NOASSERTION) · get_code("c9f502a6a946cd16")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, SamsungLabs/BoA (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.

reverse_reorder_col Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
SamsungLabs/BoA/quantizers/boa.py
pointer only (licence: NOASSERTION) · get_code("bc61e2d7ad94414b")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, SamsungLabs/BoA (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.

reverse_reorder_row Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
SamsungLabs/BoA/quantizers/boa.py
pointer only (licence: NOASSERTION) · get_code("61e1feb02fd713b4")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, SamsungLabs/BoA (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.

cleanup_memory Not yet run
unverified (harvested, no recorded run)
SamsungLabs/BoA/quantizers/boa.py
pointer only (licence: NOASSERTION) · get_code("b9b9db4928482dd1")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, SamsungLabs/BoA (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.

Also present in other papers' code

Of 11 samples lifted from this paper's linked repositories, 11 carry a function identity and 0 do not. Of the 11 distinct functions with an identity, 5 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 5 later) and 6 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
cleanup_memory
brick of this paper's assembly: helper
1 other paper
1 later · 1 only as an assembly brick
2602.04929 (2026-02)
TurboBoA: Faster and Exact Attention-aware Quantization without Backpropagation
damping
brick of this paper's assembly: helper
1 other paper
1 later · 1 only as an assembly brick
2602.04929 (2026-02)
TurboBoA: Faster and Exact Attention-aware Quantization without Backpropagation
fake_quantize
brick of this paper's assembly: helper
1 other paper
1 later · 1 only as an assembly brick
2602.04929 (2026-02)
TurboBoA: Faster and Exact Attention-aware Quantization without Backpropagation
get_cholesky_of_inverse
brick of this paper's assembly: helper
1 other paper
1 later · 1 only as an assembly brick
2602.04929 (2026-02)
TurboBoA: Faster and Exact Attention-aware Quantization without Backpropagation
quantize
brick of this paper's assembly: helper
1 other paper
1 later · 1 only as an assembly brick
2602.04929 (2026-02)
TurboBoA: Faster and Exact Attention-aware Quantization without Backpropagation

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

Post-training quantization (PTQ) is a promising solution for deploying large language models (LLMs) on resource-constrained devices. Early methods developed for small-scale networks, such as ResNet, rely on gradient-based optimization, which becomes impractical for hyper-scale LLMs with billions of parameters. While recently proposed backpropagation-free or transformationbased methods alleviate this issue, they ignore inter-layer interactions or use the naïve nearestrounding-based quantized weight assignment to save the heavy computational cost of weight optimization. In this paper, we introduce a novel backpropagation-free PTQ algorithm that optimizes quantized weights by considering interlayer dependencies. The key innovation is the development of attention-aware Hessian matrices that capture inter-layer interactions within the attention module. Extensive experiments demonstrate that our approach not only outperforms existing weight quantization methods but also shows good synergy with conventional methods to suppress activation outliers, leading to stateof-the-art weight-activation quantization performance. The code will be available at https: //github.com/SamsungLabs/BoA.

For agents

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

get_harvested_code_for_paper("2406.13474")
get_code_for_paper("2406.13474")
have("2406.13474")

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

curl https://syntology.ai/api/ran/2406.13474.json

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

[![Syntology run record](https://syntology.ai/api/ran/2406.13474.svg)](https://syntology.ai/paper/2406.13474)

Connect an agent — have() is free.