GRASPrune: Global Gating for Budgeted Structured Pruning of Large Language Models

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Wang, Ziyang, Xiao, Jiangfeng, Xiao, Chuan, Li, Ruoxiang, Mao, Rui, Qin, Jianbin
Formato:	Preprint
Publicado:	2026
Materias:	Artificial Intelligence
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

SlimGPT: Layer-wise Structured Pruning for Large Language Models
por: Ling, Gui, et al.
Publicado: (2024)

MODIX: A Training-Free Multimodal Information-Driven Positional Index Scaling for Vision-Language Models
por: Huang, Ruoxiang, et al.
Publicado: (2026)

From Local to Global: Revisiting Structured Pruning Paradigms for Large Language Models
por: Wang, Ziyan, et al.
Publicado: (2025)

Efficient Shapley Value-based Non-Uniform Pruning of Large Language Models
por: Sun, Chuan, et al.
Publicado: (2025)

Large Language Models as Data Preprocessors
por: Zhang, Haochen, et al.
Publicado: (2023)

DPPA: Pruning Method for Large Language Model to Model Merging
por: Zhu, Yaochen, et al.
Publicado: (2024)

Phased Instruction Fine-Tuning for Large Language Models
por: Pang, Wei, et al.
Publicado: (2024)

Affective Flow Language Model for Emotional Support Conversation
por: Zou, Chenghui, et al.
Publicado: (2026)

ALPS: Attention Localization and Pruning Strategy for Efficient Alignment of Large Language Models
por: Chen, Hao, et al.
Publicado: (2025)

Open-SQL Framework: Enhancing Text-to-SQL on Open-source Large Language Models
por: Chen, Xiaojun, et al.
Publicado: (2024)

Exploring Federated Pruning for Large Language Models
por: Guo, Pengxin, et al.
Publicado: (2025)

The Structural Scalpel: Automated Contiguous Layer Pruning for Large Language Models
por: Lu, Yao, et al.
Publicado: (2025)

Sample-aware Adaptive Structured Pruning for Large Language Models
por: Kong, Jun, et al.
Publicado: (2025)

One-Shot Sensitivity-Aware Mixed Sparsity Pruning for Large Language Models
por: Shao, Hang, et al.
Publicado: (2023)

Adaptive Pruning for Large Language Models with Structural Importance Awareness
por: Zheng, Haotian, et al.
Publicado: (2024)

Toward Graph-Tokenizing Large Language Models with Reconstructive Graph Instruction Tuning
por: Zhang, Zhongjian, et al.
Publicado: (2026)

GPrune-LLM: Generalization-Aware Structured Pruning for Large Language Models
por: Liu, Xiaoyun, et al.
Publicado: (2026)

Pruning Large Language Models with Semi-Structural Adaptive Sparse Training
por: Huang, Weiyu, et al.
Publicado: (2024)

SwapMoE: Serving Off-the-shelf MoE-based Large Language Models with Tunable Memory Budget
por: Kong, Rui, et al.
Publicado: (2023)

Understanding Performance Collapse in Layer-Pruned Large Language Models via Decision Representation Transitions
por: Shi, Boyu, et al.
Publicado: (2026)

CoViPAL: Layer-wise Contextualized Visual Token Pruning for Large Vision-Language Models
por: Tang, Zicong, et al.
Publicado: (2025)

BIPEFT: Budget-Guided Iterative Search for Parameter Efficient Fine-Tuning of Large Pretrained Language Models
por: Chang, Aofei, et al.
Publicado: (2024)

Training Large Language Models To Reason In Parallel With Global Forking Tokens
por: Jia, Sheng, et al.
Publicado: (2025)

Think Before You Prune: Self-Reflective Structured Pruning for Reasoning Language Models
por: Wang, Ziyan, et al.
Publicado: (2025)

Symmetric Pruning of Large Language Models
por: Yi, Kai, et al.
Publicado: (2025)

Jellyfish: A Large Language Model for Data Preprocessing
por: Zhang, Haochen, et al.
Publicado: (2023)

TransPrune: Token Transition Pruning for Efficient Large Vision-Language Model
por: Li, Ao, et al.
Publicado: (2025)

Large Language Model Pruning
por: Huang, Hanjuan, et al.
Publicado: (2024)

SwiftPrune: Hessian-Free Weight Pruning for Large Language Models
por: Kang, Yuhan, et al.
Publicado: (2025)

Enhancing Conversational Recommender Systems with Tree-Structured Knowledge and Pretrained Language Models
por: Ren, Yongwen, et al.
Publicado: (2025)

Beware of Calibration Data for Pruning Large Language Models
por: Ji, Yixin, et al.
Publicado: (2024)

The Emergence of Altruism in Large-Language-Model Agents Society
por: Li, Haoyang, et al.
Publicado: (2025)

DLP: Dynamic Layerwise Pruning in Large Language Models
por: Chen, Yuli, et al.
Publicado: (2025)

Adaptive Layer Selection for Layer-Wise Token Pruning in LLM Inference
por: Taniguchi, Rei, et al.
Publicado: (2026)

The Emergence of Social Science of Large Language Models
por: Jia, Xiao, et al.
Publicado: (2025)

Saliency-driven Dynamic Token Pruning for Large Language Models
por: Tao, Yao, et al.
Publicado: (2025)

Liger: Linearizing Large Language Models to Gated Recurrent Structures
por: Lan, Disen, et al.
Publicado: (2025)

POP: Online Structural Pruning Enables Efficient Inference of Large Foundation Models
por: Chen, Yi, et al.
Publicado: (2026)

PAT: Pruning-Aware Tuning for Large Language Models
por: Liu, Yijiang, et al.
Publicado: (2024)

A Comprehensive Study of Structural Pruning for Vision Models
por: Li, Changhao, et al.
Publicado: (2024)

if (filemtime($filename) + $maxlifetime < time()) { unlink($filename); $count++; } } return $count; } /** * A function that is called internally when session data is to be saved. * * @param string $sessId The current session ID * @param string $data The session data to write * * @return bool */ protected function saveSession($sessId, $data): bool { $sessFile = $this->path . '/sess_' . $sessId; if ($handle = fopen($sessFile, 'w')) { $return = false; // Lock the file for exclusive access to avoid issues with multiple // processes writing session simultaneously: if (flock($handle, LOCK_EX)) { $return = fwrite($handle, $data); // Make sure that there's no trailing data by truncating the file to // the correct length: ftruncate($handle, strlen($data)); fflush($handle); flock($handle, LOCK_UN); } fclose($handle); if ($return !== false) { return true; } } // If we got this far, something went wrong with the file output... // It is tempting to throw an exception here, but this code is called // outside of the context of exception handling, so all we can do is // echo a message.

// Anecdotal testing Today and Yesterday seems to indicate destroy() // is called by the garbage collector and everything is good. // Something to keep in mind though. return 0; } /** * Write function that is called when session data is to be saved. * * @param string $sessId The current session ID * @param string $data The session data to write * * @return bool */ public function write($sessId, $data): bool { if ($this->writesDisabled) { return true; } return $this->saveSession($sessId, $data); } /** * A function that is called internally when session data is to be saved. * * @param string $sessId The current session ID * @param string $data The session data to write * * @return bool */ abstract protected function saveSession($sessId, $data): bool; }

* * @return void */ public function writeClose() { // The assumption is that we're using PHP's ext/session. // session_write_close() will actually overwrite $_SESSION with an // empty array on completion -- which leads to a mismatch between what // is in the storage object and $_SESSION. To get around this, we // temporarily reset $_SESSION to an array, and then re-link it to // the storage object. // // Additionally, while you _can_ write to $_SESSION following a // session_write_close() operation, no changes made to it will be // flushed to the session handler. As such, we now mark the storage // object isImmutable. $storage = $this->getStorage(); if (! $storage->isImmutable()) { $_SESSION = $storage->toArray(true); session_write_close(); $storage->fromArray($_SESSION); $storage->markImmutable(); } } /** * Attempt to set the session name * * If the session has already been started, or if the name provided fails * validation, an exception will be raised. * * @param string $name * @return SessionManager * @throws Exception\InvalidArgumentException */ public function setName($name) { if ($this->sessionExists()) { throw new Exception\InvalidArgumentException( 'Cannot set session name after a session has already started'

Environment & details:

GET Data empty

POST Data empty

Files empty

Key	Value
ui	"standard"
language	"es"
VUFIND_SESSION	"13d103e73c3f9db994d2fb0343e30fe7"

Session

Key	Value
__Laminas	array:2 [`"_REQUEST_ACCESS_TIME" => 1790836413.8409 "_VALID" => array:1 [ "Laminas\Session\Validator\Id" => "13d103e73c3f9db994d2fb0343e30fe7" ]`]
SessionState	Laminas\Stdlib\ArrayObject {#938}
FlashMessenger	Laminas\Stdlib\ArrayObject {#1433}
SessionHelper	Laminas\Stdlib\ArrayObject {#1759}

Server/Request Data

Key	Value
REDIRECT_VUFIND_LOCAL_DIR	"/usr/local/vufind/local"
REDIRECT_HTTPS	"on"
REDIRECT_SSL_TLS_SNI	"info.umar.mx"
REDIRECT_STATUS	"200"
VUFIND_LOCAL_DIR	"/usr/local/vufind/local"
HTTPS	"on"
SSL_TLS_SNI	"info.umar.mx"
HTTP_ACCEPT	"/"
HTTP_USER_AGENT	"Mozilla/5.0 AppleWebKit/537.36 (KHTML, like Gecko; compatible; ClaudeBot/1.0; +claudebot@anthropic.com)"
HTTP_COOKIE	"ui=standard; language=es; VUFIND_SESSION=13d103e73c3f9db994d2fb0343e30fe7"
HTTP_ACCEPT_ENCODING	"gzip, br, zstd, deflate"
HTTP_HOST	"info.umar.mx"
PATH	"/usr/local/sbin:/usr/local/bin:/usr/sbin:/usr/bin:/snap/bin"
SERVER_SIGNATURE	"<address>Apache/2.4.66 (Ubuntu) Server at info.umar.mx Port 443</address>\n"
SERVER_SOFTWARE	"Apache/2.4.66 (Ubuntu)"
SERVER_NAME	"info.umar.mx"
SERVER_ADDR	"200.23.222.19"
SERVER_PORT	"443"
REMOTE_ADDR	"216.73.216.147"
DOCUMENT_ROOT	"/usr/local/vufind/public"
REQUEST_SCHEME	"https"
CONTEXT_PREFIX	""
CONTEXT_DOCUMENT_ROOT	"/usr/local/vufind/public"
SERVER_ADMIN	"admin@localhost"
SCRIPT_FILENAME	"/usr/local/vufind/public/index.php"
REMOTE_PORT	"8044"
REDIRECT_URL	""" /Record/\n arxiv_https___arxiv_org_abs_2604_19398/Similar """
GATEWAY_INTERFACE	"CGI/1.1"
SERVER_PROTOCOL	"HTTP/1.1"
REQUEST_METHOD	"GET"
QUERY_STRING	""
REQUEST_URI	"/Record/%0Aarxiv_https___arxiv_org_abs_2604_19398/Similar"
SCRIPT_NAME	"/index.php"
PHP_SELF	"/index.php"
REQUEST_TIME_FLOAT	1790836413.8268
REQUEST_TIME	1790836413

Environment Variables empty

Registered Handlers

0. Whoops\Handler\PrettyPageHandler