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
A Two Stage Low Power 0.73-4.4 GHz LNA Using Current Reuse and Noise Reduction Techniques
Sajjad Shojaei Baghini - Seyed-Ali Samareh-TaheriNasab - Samad Sheikhaei
A Multi-domain Fuzzy Ensemble Approach for Epileptic Seizure Detection
Samin Shahraki - Alireza Hajabdollah javaheri - Mahdi Pourgholi - Pedram Safarpour
Current Re-use RF Receiver Front-End Topology Combinding LNA, Mixer, VCO and Frequency Divider
Ayda Zamani Ahari - Saeed Saeedi
Human Action Recognition in Still Images Using ConViT
Seyed Rohollah Hosseyni - Sanaz Seyedin - Hassan Taheri
Flexible Generation Expansion Planning Considering Representative Days of Load and Renewable Variations
Peyman Amirian - Zeinab Maleki - Mohammad-Amin Pourmoosavi - Turaj Amraee
ساخت حسگر گاز بر پایه ی گرافن اکساید و سیلیکون متخلخل
سیده صفیه رضایی - مینا امیر مزلقانی
Innovative Pathway Optimization for Autonomous Drones in Urban Landscapes Using Integrated Techniques
Seyed Ahmad Abtahi - M.A. Amiri Atashgah - Bahram Tarvirdizadeh - Mohammad Habashiniak
Exploring the Impact of Machine Translation on Fake News Detection: A Case Study on Persian Tweets about COVID-19
Masood Hamed Saghayan - Seyedeh Fatemeh Ebrahimi - Mohammad Bahrani
Net Load Forecasting of Household Prosumers Considering Deep Reinforcement Learning
Behzad Motallebi Azar - Rasool Kazemzadeh - Morteza Zare Oskouei - Behnam Mohammadi-Ivatloo
Analyzing, simulating and measuring the effects of stirrers and walls on the performance of the RTS60 reverberation chamber
Mojtaba Basravi - Zakerhossein Firouzeh - Hadi Aliakbarian
بیشتر
ثمین همایش، سامانه مدیریت کنفرانس ها و جشنواره ها - نگارش 44.7.2
