Papers › SVD-LLM V2: Optimizing Singular Value Truncation for Large Language Model Compression

SVD-LLM V2: Optimizing Singular Value Truncation for Large Language Model Compression

16 Mar 2025arXiv:2503.12340archive 2025-07-28

Xin Wang, Samiul Alam, Zhongwei Wan, Hui Shen, Mi Zhang

Despite significant advancements, the practical deployment of Large Language Models (LLMs) is often hampered by their immense sizes, highlighting the need for effective compression techniques. Singular Value Decomposition (SVD) is a promising LLM compression technique. However, existing SVD-based compression methods fall short in reducing truncation losses, leading to less competitive performance in compressed models. In this work, we introduce SVD-LLM V2, a SVD-based LLM compression method that optimizes singular value truncation in SVD compression with two techniques. First, SVD-LLM V2 proposes to use theoretical truncation loss of weight matrices to assign a unique compression ratio to each weight matrix at different layers to accommodate weight redundancy heterogeneity. Second, SVD-LLM V2 proposes loss-optimized weight truncation to ensure that the truncated singular values result in a lower and more stable truncation loss in practice. We evaluate SVD-LLM V2 on ten datasets and five LLMs at various scales. Our results show SVD-LLM V2 outperforms state-of-the-art SVD-based LLM compression methods. Our code is available at https://github.com/AIoT-MLSys-Lab/SVD-LLM

PaperPDFCodeCode Syntology ranMethod as code

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 12 code samples harvested from 1 repository linked to this paper: 9 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 1 honoured, 0 violated, 6 with no contract checked; 2 where Syntology's instrument failed) · 3 unverified. Where Syntology's instrument failed: 2 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: official repository: 12 samples from 1 repository, 9 ran (7 with no instrument failure; 2 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 between 2026-09-22 and 2026-09-24 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

aiot-mlsys-lab/svd-llm officialmentioned in papermentioned on GitHubpytorchSyntology: 12 samples, 9 ran (2 instrument-failed) · 3 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

12 samples harvested: 9 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 1 honoured, 0 violated, 6 with no contract checked; 2 where Syntology's instrument failed) · 3 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page has not changed since , the first build that kept a record date for it; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

1ran · honoured contract
2ran; the contract check could not run
6ran
3unverified

Licence: 0 of the 12 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 aiot-mlsys-lab/svd-llm. “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. A census tag appears when Syntology's census ran implementations with that name on one shared input per bucket: it gives how many were compared, from how many papers, and how many distinct outputs they produced, and names this sample's bucket when this sample was one of them.

aiot-mlsys-lab/svd-llm official repository 12 samples, 9 ran (2 instrument-failed) · 3 unverified
LlamaRotaryEmbedding in 13 papers SVDLLM.py ran · metamorphic tier: invariant fingerprinted Apache-2.0 (permissive) · c4daf2f7ed4b51f9 · report fixture: signature x:Tensor/3/float, seq_len:int/0/int · returned tuple · level recorded 2026-09-22
MistralRotaryEmbedding SVDLLM.py ran · metamorphic tier: invariant fingerprinted Apache-2.0 (permissive) · 1b2e87c411e2d8bc · report fixture: signature x:Tensor/3/float, seq_len:int/0/int · returned tuple · level recorded 2026-09-22
SVDOPTAttention SVDLLM.py ran fingerprinted Apache-2.0 (permissive) · 041ad30174c9bdee · report fixture: signature hidden_states:Tensor/3/float, key_value_states:NoneType/0/?, past_key_value:NoneType/0/?, attention_mask:NoneType/0/?, layer_head_mask:NoneType/0/?, output_attentions:bool/0/bool · returned tuple · level recorded 2026-09-24
SVD_LlamaAttention SVDLLM.py ran Apache-2.0 (permissive) · 8a5b8f50673d8352 · report fixture: signature hidden_states:Tensor/3/float, attention_mask:NoneType/0/?, position_ids:Tensor/2/int, past_key_value:NoneType/0/?, output_attentions:bool/0/bool, use_cache:bool/0/bool · returned tuple · level recorded 2026-09-24
SVD_LlamaMLP SVDLLM.py ran Apache-2.0 (permissive) · 77e1446ab4ce2b75 · report fixture: signature x:Tensor/2/float · returned Tensor · level recorded 2026-09-24
SVD_MistralMLP SVDLLM.py ran fingerprinted Apache-2.0 (permissive) · 3009ebbba1aa5922 · report fixture: signature x:Tensor/2/float · returned Tensor · level recorded 2026-09-24
apply_rotary_pos_emb in 393 papers
census: 14 implementations from 15 papers, 8 distinct outputs across 7 buckets, one shared input per bucket
SVDLLM.py ran; the contract check could not run (RAISES) Apache-2.0 (permissive) · af9e30f5a1fe133e · report fixture: signature q:Tensor/4/float, k:Tensor/4/float, cos:Tensor/4/float, sin:Tensor/4/float, position_ids:Tensor/2/int · returned tuple · level recorded 2026-09-22
repeat_kv in 244 papers
census: 15 implementations from 60 papers, 2 distinct outputs on one shared input this sample: bucket 1 of 1, arg 1: rank 4, kind float, dtype float32
SVDLLM.py ran; the contract check could not run (RAISES) fingerprinted Apache-2.0 (permissive) · 25ef0712acc702e7 · report fixture: signature hidden_states:Tensor/4/float, n_rep:int/0/int · returned Tensor · level recorded 2026-09-22
rotate_half in 424 papers
census: 24 implementations from 96 papers, 4 distinct outputs across 2 buckets, one shared input per bucket this sample: bucket 1 of 2, arg 1: rank 2, kind float, dtype float32
SVDLLM.py ran · honoured contract fingerprinted Apache-2.0 (permissive) · 2a2393c46243da08 · report fixture: signature x:Tensor/2/float · returned Tensor · level recorded 2026-09-22
SVDOPTDecoderLayer SVDLLM.py unverified Apache-2.0 (permissive) · 88545df842057010 · report
SVD_MistralAttention SVDLLM.py unverified Apache-2.0 (permissive) · 656c1a145aa666cb · report
whitening_local_update SVDLLM.py unverified Apache-2.0 (permissive) · d0b633b47c9a7133 · report

Method as code Syntology

What Syntology's graph records as this paper's claimed method, lifted into code: each assembly names its bricks (functions and classes), each with its own role and its own verification level. An assembly is not a check that the code implements the method correctly or reproduces the paper's results. Levels are each brick's own verification level in Syntology's graph (level 0: no recorded run), listed brick by brick and never combined into one level; “ran” means the brick executed on a synthesized input, not that its output is correct, and the instrument figure counts failures of Syntology's instrument, not of the code. Where a model read the code against the paper's claim, each assembly's label verdict is one model's judgement, kept in this page's JSON twin; it is not calibrated, so no card prints it.

1 assembly on this paper: 1 harvested, 0 generated.

harvested Assembly for SVD-LLM V2 (graph method: SVD-LLM V2). 13 bricks; individually on a fixture: 10 ran (of which 1 constructed an object rather than computing a result; 8 with no instrument failure: 1 honoured, 0 violated, 7 with no contract checked; 2 where Syntology's instrument failed) · 3 unverified. The assembly has not been run end-to-end.

  1. whitening_local_update entry · level 0 · unverified · d0b633b47c9a7133
  2. SVDOPTDecoderLayer helper · level 0 · unverified · 88545df842057010
  3. SVD_LlamaAttention helper · level 1 · ran · 8a5b8f50673d8352
  4. SVD_LlamaMLP helper · level 1 · ran · 77e1446ab4ce2b75
  5. SVD_MistralAttention helper · level 0 · unverified · 656c1a145aa666cb
  6. SVD_MistralMLP helper · level 1 · ran · 3009ebbba1aa5922
  7. local_update update_rule · level 1 · ran · af6cabbec62ab935
  8. SVDOPTAttention helper · level 1 · ran · 041ad30174c9bdee
  9. LlamaRotaryEmbedding helper · level 1 · ran · c4daf2f7ed4b51f9
  10. apply_rotary_pos_emb helper · level 1 · ran; the contract check could not run (RAISES) · af9e30f5a1fe133e
  11. MistralRotaryEmbedding helper · level 1 · ran · 1b2e87c411e2d8bc
  12. repeat_kv helper · level 1 · ran; the contract check could not run (RAISES) · 25ef0712acc702e7
  13. rotate_half helper · level 1 · ran · honoured contract · 2a2393c46243da08

Each brick ends with its code_sha256, Syntology's identity for that exact code; click one to copy the get_code call that returns it. For agents, on Syntology's MCP service: assembly(arxiv_id="2503.12340") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

Language ModelingLanguage ModellingLarge Language ModelModel Compression

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

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