Quantization of Deep Learning Solution for Efficient Inference | Kim Hee, UMM [PyData Südwest]

Показать описание

The power consumption of data-center is doubling every year and edge devices like Internet of Things (IoT) are growing rapidly. Quantize deep learning model reduces model size and inference time with little to no loss of model accuracy. Background of the core concepts and some results will be presented during the presentation.

Kim Hee
UMM Medizinische Fakultät Mannheim / Biomedizinische Informatik

PyData is an educational program of NumFOCUS, a 501(c)3 non-profit organization in the United States. PyData provides a forum for the international community of users and developers of data analysis tools to share ideas and learn from each other. The global PyData network promotes discussion of best practices, new approaches, and emerging technologies for data management, processing, analytics, and visualization. PyData communities approach data science using many languages, including (but not limited to) Python, Julia, and R.

PyData conferences aim to be accessible and community-driven, with novice to advanced level presentations. PyData tutorials and talks bring attendees the latest project features along with cutting-edge use cases. 00:00 Welcome!
00:10 Help us add time stamps or captions to this video! See the description for details.

Рекомендации по теме

Quantization of Deep Learning Solution for Efficient Inference | Kim Hee, UMM [PyData Südwest]

Quantization of Deep Learning Solution for Efficient Inference | Kim Hee, UMM [PyData Südwest]

Quantization in Deep Learning (LLMs)

ICLR Paper: Learn Step Size Quantization

Leaner and Greener AI with Quantization in PyTorch - SURAJ SUBRAMANIAN

tinyML Talks: A Practical Guide to Neural Network Quantization

Quantization in Neural Networks - May 27, 2020

Quantization in Neural Networks - Basics Explained | Affine and Symmetric Quantization

Quantization explained with PyTorch - Post-Training Quantization, Quantization-Aware Training

How DeepSeek Rewrote Quantization Part 1 | Mixed Precision | Fine-grained quantization

Training Quantized Neural Networks With a Full-Precision Auxiliary Module

Quantum 101 Episode 2: Quantization Explained

Automatic Neural Network Compression by Sparsity-Quantization Joint Learning: A Constrained...

tinymL Summit 2022: Model Optimization with QKeras’ Quantization-Aware Training and Vizier’s...

How Quantization Makes AI Models Faster and More Efficient

Introduction to the quantization of neural networks

8-Bit Quantisation Demistyfied With Transformers : A Solution For Reducing LLM Sizes

Adaptive Loss-Aware Quantization for Multi-Bit Networks

SPIQ: Data-Free Static Per-Channel Input Quantization

Data-Free Parameter Pruning and Quantization

[TECHCON'20] Overwrite Quantization: Opportunistic Outlier Handling for Neural Network Accelera...

EfficientML.ai Lecture 5 - Quantization (Part I) (MIT 6.5940, Fall 2023)

tinyML Research Symposium 2021: Quantization-Guided Training for Compact TinyML Models

tinyML Asia 2020 Kai YU: Structured Quantization for Neural Network Language Model Compression

[REFAI Seminar 08/31/21] Efficient AI via Extreme Network Quantization and Binarization