Papers › DLP: Dynamic Layerwise Pruning in Large Language Models

DLP: Dynamic Layerwise Pruning in Large Language Models

27 May 2025arXiv:2505.23807archive 2025-07-28

Yuli Chen, Bo Cheng, Jiale Han, Yingying Zhang, Yingting Li, Shuhao Zhang

Pruning has recently been widely adopted to reduce the parameter scale and improve the inference efficiency of Large Language Models (LLMs). Mainstream pruning techniques often rely on uniform layerwise pruning strategies, which can lead to severe performance degradation at high sparsity levels. Recognizing the varying contributions of different layers in LLMs, recent studies have shifted their focus toward non-uniform layerwise pruning. However, these approaches often rely on pre-defined values, which can result in suboptimal performance. To overcome these limitations, we propose a novel method called Dynamic Layerwise Pruning (DLP). This approach adaptively determines the relative importance of each layer by integrating model weights with input activation information, assigning pruning rates accordingly. Experimental results show that DLP effectively preserves model performance at high sparsity levels across multiple LLMs. Specifically, at 70% sparsity, DLP reduces the perplexity of LLaMA2-7B by 7.79 and improves the average accuracy by 2.7% compared to state-of-the-art methods. Moreover, DLP is compatible with various existing LLM compression techniques and can be seamlessly integrated into Parameter-Efficient Fine-Tuning (PEFT). We release the code at https://github.com/ironartisan/DLP to facilitate future research.

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 10 code samples harvested from 1 repository linked to this paper: 0 ran · 10 unverified.

By repository: official repository: 10 samples from 1 repository, 0 ran (0 with no instrument failure; 0 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.

ironartisan/dlp officialmentioned in papermentioned on GitHubpytorchSyntology: 10 samples, 0 ran · 10 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

10 samples harvested: 0 ran · 10 unverified. 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.

10unverified

Licence: 0 of the 10 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 ironartisan/dlp. “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. “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.

ironartisan/dlp official repository 10 samples, 0 ran · 10 unverified
WrappedGPT in 6 papers lib/prune.py unverified Apache-2.0 (permissive) · c8eb582a1c308afe · report
get_c4 in 41 papers lib/prune.py unverified Apache-2.0 (permissive) · c668683d68ff5099 · report
get_dlp_ratios lib/prune.py unverified Apache-2.0 (permissive) · bc4ca91c9242b32f · report
get_dlp_structure_ratios lib/prune.py unverified Apache-2.0 (permissive) · b28bde5b41cc1c86 · report
get_loaders in 51 papers lib/prune.py unverified Apache-2.0 (permissive) · 2eaf81f9b2452228 · report
get_ptb in 43 papers lib/prune.py unverified Apache-2.0 (permissive) · 6286af97d1bc3835 · report
get_wikitext2 in 78 papers lib/prune.py unverified Apache-2.0 (permissive) · dd6b0a913778761d · report
prepare_calibration_input_opt lib/prune.py unverified Apache-2.0 (permissive) · e4d334bd3c44b2c4 · report
prune_wanda_dlp lib/prune.py unverified Apache-2.0 (permissive) · b11c3039afd17a76 · report
prune_wanda_dlp lib/prune.py unverified Apache-2.0 (permissive) · 8f990c5a3cfb6939 · 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 DLP (graph method: DLP). 11 bricks; individually on a fixture: 3 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 2 where Syntology's instrument failed) · 8 unverified. The assembly has not been run end-to-end.

  1. prune_wanda_dlp entry · level 0 · unverified · 8f990c5a3cfb6939
  2. WrappedGPT helper · level 0 · unverified · c8eb582a1c308afe
  3. find_layers helper · level 1 · ran · our draft was wrong · 2ed16fcdc14ad951
  4. get_loaders helper · level 0 · unverified · 2eaf81f9b2452228
  5. prepare_calibration_input helper · level 0 · unverified · 298323fc64be86fa
  6. prepare_calibration_input_opt helper · level 0 · unverified · e4d334bd3c44b2c4
  7. return_given_alpha helper · level 1 · ran; the contract check could not run · d79ce728b3ab7682
  8. get_c4 helper · level 0 · unverified · c668683d68ff5099
  9. get_ptb helper · level 0 · unverified · 6286af97d1bc3835
  10. get_wikitext2 helper · level 0 · unverified · dd6b0a913778761d
  11. TokenizerWrapper helper · level 1 · ran · 37d49ff5ade0a79c

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="2505.23807") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

parameter-efficient fine-tuning

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

FocusPruning

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