لطفا منتظر بمانید ...
0% Complete
صفحه اصلی
/
سی و چهارمین کنفرانس بین المللی مهندسی برق
Efficient Large Language Models with Zero-Shot Adjustable Acceleration
نویسندگان :
Sajjad Kachuee
1
Mohammad Sharifkhani
2
1- دانشگاه صنعتی شریف
2- دانشگاه صنعتی شریف
کلمات کلیدی :
Zero-Shot Adjustable Acceleration،Preservation Rate،Hidden Activation،Context Contribution
چکیده :
Large Language Models (LLMs) face significant challenges in real-world applications, particularly in balancing computational efficiency and model performance. Acceleration during both fine-tuning and inference is essential for designing efficient architectures. This paper presents a novel training and inference method, termed zero-shot adjustable acceleration, which dynamically adjusts hardware utilization at inference time without additional fine-tuning. The method is applied to recent LLMs and evaluated on multiple classification and text generation benchmarks. Experimental results demonstrate that the approach enables flexible zero-shot acceleration and achieves up to an 11× speedup over baseline methods, while maintaining high model performance.
لیست مقالات
لیست مقالات بایگانی شده
Extension Network of Radiomics-based Deeply Supervised U-Net (ERDU) For Prostate Image Segmentation
Mahdi Ashtarian - Karim Faez - Marjan Firouznia - Hamidreza Amindavar
طبقه بندی سکته مغزی در یک سیستم دو بعدی چند فرکانسی با استفاده از امواج مایکروویو و یادگیری عمیق
محسن مهرانیان - محمدسعید ماجدی - امیررضا عطاری
The Comparison of MXene and Graphene-Based Antennas for 5G/6G Communications
Javad Shokri Seyyedi - Gholamreza Moradi - Reza Sarraf Shirazi - Sepehr Sahab - Abolfazl Ebrahimpour
Flexible Generation Expansion Planning Considering Representative Days of Load and Renewable Variations
Peyman Amirian - Zeinab Maleki - Mohammad-Amin Pourmoosavi - Turaj Amraee
Segmentation and Classification of Breast Tumors in Ultrasound Images using Adaptive Saliency of DeepLabV3+ and ResNet34 Networks
Seyede Reyhane Khorashadizade - Seyed Hamid Khatami
اثر پایلوتهای متعامد بر تخمین کانال مایمو انبوه تقسیم فرکانسی مبتنی بر رگرسیون خطی
سید طالب ساداتی لمردی - کمال محامدپور
Stray Load Losses Determination Methods of Induction Motors-A Review
Moslem Geravandi - Hassan Moradi CheshmehBeigi
Type-2 fuzzy expert system for management of smart home with combining renewable resources
Ali Beheshtikhoo - Mahdi Pourgholi - Iman Khazaee
A 2.4 GHz Low Phase Noise Voltage Controlled Oscillator With Low Supply Voltage and Robust Start-Up for WLAN Standard in 0.13µm CMOS Technology
Farzad Ramezani Sani - Mortaza Mojarad
Investigation of Statistical and Mathematical Indices for Transformer Frequency Response Analysis and Winding Condition Diagnosis Using Machine Learning Methods
Ali Ghorbani - Hossein Parsadust - Ali Khani - Mohammad Molaei
بیشتر
ثمین همایش، سامانه مدیریت کنفرانس ها و جشنواره ها - نگارش 44.7.2
