SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2403.07378 · ICLR · 2025

SVD-LLM: Truncation-aware Singular Value Decomposition for Large Language Model Compression

Yu Zheng, Mi Zhang, Xin Wang, Zhongwei Wan

arXiv · PDF · Open in the Atlas

Code that ran

1 of 3 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; 0 failures of our instrument; 2 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/2403.07378.json · badge: /api/ran/2403.07378.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
AIoT-MLSys-Lab/SVD-LLM canonical (classifier label)
classifier basis: classifier_2025
0 ran · 2 no recorded run
aiot-mlsys-lab/svd-llm marked official in Papers with Code
Papers with Code archive
1 ran · 0 no recorded run
FunctionStatusWhere it lives
local_update Ran
ran on a synthesized input · constructed an object; no result was computed
aiot-mlsys-lab/svd-llm/SVDLLM.py
code served (permissive licence) · get_code("af6cabbec62ab935")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned an instance of its own class, local_update: the run constructed the object and did not call it, so no result was computed. The image it ran in was not recorded. The code mentions cuda, and the harness aliases cuda to the CPU for every sample; whether this run needed that is not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import torch.nn as nn

torch.manual_seed(0)

# Create a small linear layer
layer = nn.Linear(in_features=3, out_features=4, bias=False)

# Create a scaling diagonal matrix (must be invertible and square)
# Shape should match the number of columns of the layer weight
scaling_diag_matrix = torch.eye(3, dtype=torch.float32)

# Set ratio parameter (compression ratio, between 0 and 1)
ratio = 0.5

# Set name parameter
name = "test_layer"

# Set direct_update parameter
direct_update = False

ARGS = {
    "layer": layer,
    "scaling_diag_matrix": scaling_diag_matrix,
    "ratio": ratio,
    "name": name,
    "direct_update": direct_update,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type local_update — the run constructed an instance of its own class and did not call it; no shape is stated — the instrument coerces any output to an array; for a local_update output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
profle_svdllm Not yet run
unverified (harvested, no recorded run)
AIoT-MLSys-Lab/SVD-LLM/SVDLLM.py
code served (permissive licence) · get_code("a1f162f2c8908c90")
How it ran

no invocation recorded.

profle_svdllm_low_resource Not yet run
unverified (harvested, no recorded run)
AIoT-MLSys-Lab/SVD-LLM/SVDLLM.py
code served (permissive licence) · get_code("3f67abd703832614")
How it ran

no invocation recorded.

Also present in other papers' code

Of 3 samples lifted from this paper's linked repositories, 3 carry a function identity and 0 do not. Of the 3 distinct functions with an identity, 3 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 3 later) and 0 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
local_update
brick of this paper's assembly: entry
1 other paper
1 later · 1 only as an assembly brick
2503.12340 (2025-03)
SVD-LLM V2: Optimizing Singular Value Truncation for Large Language Model Compression
profle_svdllm 1 other paper
1 later
2605.08314 (2026-05)
FlashSVD v1.5: Making Low-Rank Transformers Inference Actually Fast
profle_svdllm_low_resource 1 other paper
1 later
2605.08314 (2026-05)
FlashSVD v1.5: Making Low-Rank Transformers Inference Actually Fast

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

The advancements in Large Language Models (LLMs) have been hindered by their substantial sizes, which necessitates LLM compression methods for practical deployment. Singular Value Decomposition (SVD) offers a promising solution for LLM compression. However, state-of-the-art SVD-based LLM compression methods have two key limitations: truncating smaller singular values may lead to higher compression loss, and the lack of update on the compressed weights after SVD truncation. In this work, we propose SVD-LLM, a SVD-based post-training LLM compression method that addresses the limitations of existing methods. SVD-LLM incorporates a truncation-aware data whitening technique to ensure a direct mapping between singular values and compression loss. Moreover, SVD-LLM adopts a parameter update with sequential low-rank approximation to compensate for the accuracy degradation after SVD compression. We evaluate SVD-LLM on 10 datasets and seven models from three different LLM families at three different scales. Our results demonstrate the superiority of SVD-LLM over state-of-the-arts, especially at high model compression ratios.

For agents

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

get_harvested_code_for_paper("2403.07378")
get_code_for_paper("2403.07378")
have("2403.07378")

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

curl https://syntology.ai/api/ran/2403.07378.json

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

[![Syntology run record](https://syntology.ai/api/ran/2403.07378.svg)](https://syntology.ai/paper/2403.07378)

Connect an agent — have() is free.