:: Library Catalog

Gespeichert in:

Bibliographische Detailangaben
Hauptverfasser:	Shkolnik, Moran, Fishman, Maxim, Chmiel, Brian, Ben-Yaacov, Hilla, Banner, Ron, Levy, Kfir Yehuda
Format:	Preprint
Veröffentlicht:	2024
Schlagworte:	Machine Learning Artificial Intelligence Performance
Online-Zugang:	https://arxiv.org/abs/2410.03185
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Ähnliche Einträge

FP4 All the Way: Fully Quantized Training of LLMs
von: Chmiel, Brian, et al.
Veröffentlicht: (2025)

Scaling FP8 training to trillion-token LLMs
von: Fishman, Maxim, et al.
Veröffentlicht: (2024)

Normalized Architectures are Natively 4-Bit
von: Fishman, Maxim, et al.
Veröffentlicht: (2026)

Accurate Neural Training with 4-bit Matrix Multiplications at Standard Formats
von: Chmiel, Brian, et al.
Veröffentlicht: (2021)

Minimum Variance Unbiased N:M Sparsity for the Neural Gradients
von: Chmiel, Brian, et al.
Veröffentlicht: (2022)

LLMs for Analog Circuit Design Continuum (ACDC)
von: Esfandiari, Yasaman, et al.
Veröffentlicht: (2025)

ALISA: Accelerating Large Language Model Inference via Sparsity-Aware KV Caching
von: Zhao, Youpeng, et al.
Veröffentlicht: (2024)

OSCAR: Offline Spectral Covariance-Aware Rotation for 2-bit KV Cache Quantization
von: Zhou, Zhongzhu, et al.
Veröffentlicht: (2026)

Accelerating Diffusion LLMs via Adaptive Parallel Decoding
von: Israel, Daniel, et al.
Veröffentlicht: (2025)

Dynamic Expert Quantization for Scalable Mixture-of-Experts Inference
von: Chu, Kexin, et al.
Veröffentlicht: (2025)

SparAMX: Accelerating Compressed LLMs Token Generation on AMX-powered CPUs
von: AbouElhamayed, Ahmed F., et al.
Veröffentlicht: (2025)

SLiM: One-shot Quantization and Sparsity with Low-rank Approximation for LLM Weight Compression
von: Mozaffari, Mohammad, et al.
Veröffentlicht: (2024)

Unveiling the Potential of Quantization with MXFP4: Strategies for Quantization Error Reduction
von: Chhugani, Jatin, et al.
Veröffentlicht: (2026)

QJL: 1-Bit Quantized JL Transform for KV Cache Quantization with Zero Overhead
von: Zandieh, Amir, et al.
Veröffentlicht: (2024)

Energy-Aware LLMs: A step towards sustainable AI for downstream applications
von: Tran, Nguyen Phuc, et al.
Veröffentlicht: (2025)

PATCH: Learnable Tile-level Hybrid Sparsity for LLMs
von: Hourri, Younes, et al.
Veröffentlicht: (2025)

GreedySnake: Accelerating SSD-Offloaded LLM Training with Efficient Scheduling and Optimizer Step Overlapping
von: Yin, Yishu, et al.
Veröffentlicht: (2025)

Ghosted Layers: Unconstrained Activation Alignment for Recovering Layer-Pruned LLMs
von: Yun, Vincent-Daniel, et al.
Veröffentlicht: (2026)

OPTIMA: Optimal One-shot Pruning for LLMs via Quadratic Programming Reconstruction
von: Mozaffari, Mohammad, et al.
Veröffentlicht: (2025)

MoEITS: A Green AI approach for simplifying MoE-LLMs
von: Balderas, Luis, et al.
Veröffentlicht: (2026)

Model Quantization and Hardware Acceleration for Vision Transformers: A Comprehensive Survey
von: Du, Dayou, et al.
Veröffentlicht: (2024)

Unleashing Automated Congestion Control Customization in the Wild
von: Cohen, Amit, et al.
Veröffentlicht: (2025)

Quamba2: A Robust and Scalable Post-training Quantization Framework for Selective State Space Models
von: Chiang, Hung-Yueh, et al.
Veröffentlicht: (2025)

Accelerating AI Performance using Anderson Extrapolation on GPUs
von: Dajani, Saleem Abdul Fattah Ahmed Al, et al.
Veröffentlicht: (2024)

QServe: W4A8KV4 Quantization and System Co-design for Efficient LLM Serving
von: Lin, Yujun, et al.
Veröffentlicht: (2024)

REAM: Merging Improves Pruning of Experts in LLMs
von: Jha, Saurav, et al.
Veröffentlicht: (2026)

Automatic Generation of Fast and Accurate Performance Models for Deep Neural Network Accelerators
von: Lübeck, Konstantin, et al.
Veröffentlicht: (2024)

It's all about PR -- Smart Benchmarking AI Accelerators using Performance Representatives
von: Jung, Alexander Louis-Ferdinand, et al.
Veröffentlicht: (2024)

A Performance Evaluation of a Quantized Large Language Model on Various Smartphones
von: Çöplü, Tolga, et al.
Veröffentlicht: (2023)

FlexiSAGA: A Flexible Systolic Array GEMM Accelerator for Sparse and Dense Processing
von: Müller, Mika Markus, et al.
Veröffentlicht: (2025)

KernelBench: Can LLMs Write Efficient GPU Kernels?
von: Ouyang, Anne, et al.
Veröffentlicht: (2025)

RooflineBench: A Benchmarking Framework for On-Device LLMs via Roofline Analysis
von: Bi, Zhen, et al.
Veröffentlicht: (2026)

Kevin: Multi-Turn RL for Generating CUDA Kernels
von: Baronio, Carlo, et al.
Veröffentlicht: (2025)

Enhancing Energy-Awareness in Deep Learning through Fine-Grained Energy Measurement
von: Rajput, Saurabhsingh, et al.
Veröffentlicht: (2023)

Policy Gradient with Tree Search: Avoiding Local Optimas through Lookahead
von: Koren, Uri, et al.
Veröffentlicht: (2025)

QPART: Adaptive Model Quantization and Dynamic Workload Balancing for Accuracy-aware Edge Inference
von: Li, Xiangchen, et al.
Veröffentlicht: (2025)

FlashSVD: Memory-Efficient Inference with Streaming for Low-Rank Models
von: Shao, Zishan, et al.
Veröffentlicht: (2025)

Reducing Latency of LLM Search Agent via Speculation-based Algorithm-System Co-Design
von: Huang, Zixiao, et al.
Veröffentlicht: (2025)

Quantum Neural Networks for Wind Energy Forecasting: A Comparative Study of Performance and Scalability with Classical Models
von: Hangun, Batuhan, et al.
Veröffentlicht: (2025)

Deploying Open-Source Large Language Models: A performance Analysis
von: Bendi-Ouis, Yannis, et al.
Veröffentlicht: (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"
VUFIND_SESSION	"a575e7fa58a8d30e2836268fbb05543c"
language	"de"

Session

Key	Value
__Laminas	array:2 [`"_REQUEST_ACCESS_TIME" => 1784386146.9393 "_VALID" => array:1 [ "Laminas\Session\Validator\Id" => "a575e7fa58a8d30e2836268fbb05543c" ]`]
SessionState	Laminas\Stdlib\ArrayObject {#938}
FlashMessenger	Laminas\Stdlib\ArrayObject {#1583}
SessionHelper	Laminas\Stdlib\ArrayObject {#1772}

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; VUFIND_SESSION=a575e7fa58a8d30e2836268fbb05543c; language=de"
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	"216.73.217.30"
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	"20055"
REDIRECT_URL	""" /Record/\n arxiv_https___arxiv_org_abs_2410_03185/Similar """
GATEWAY_INTERFACE	"CGI/1.1"
SERVER_PROTOCOL	"HTTP/1.1"
REQUEST_METHOD	"GET"
QUERY_STRING	""
REQUEST_URI	"/Record/%0Aarxiv_https___arxiv_org_abs_2410_03185/Similar"
SCRIPT_NAME	"/index.php"
PHP_SELF	"/index.php"
REQUEST_TIME_FLOAT	1784386146.9324
REQUEST_TIME	1784386146

Environment Variables empty

Registered Handlers

0. Whoops\Handler\PrettyPageHandler