Видео

EfficientML.ai Lecture 1 - Introduction (MIT 6.5940, Fall 2024) Lecture 1: Introduction Instructor: Prof. Song Han Slides: efficientml.ai

ISCA 2024 Atomique: A Quantum Compiler for Reconfigurable Neutral Atom Arrays Hanrui Wang, Pengyu Liu, Daniel Bochen Tan, Yilian Liu, Jiaqi Gu, David Z. Pan, Jason Cong, Umut Acar, Song Han The neutral atom array has gained prominence in quantum computing for its scalability and operation fidelity. Previous works focus on fixed atom arrays (FAAs) that require extensive SWAP operations for long-...

Talk video for MLSys 2024 Best Paper: "AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration" (May 14th at Santa Clara Convention Center, CA, US) Ji Lin*, Jiaming Tang*, Haotian Tang†, Shang Yang†, Wei-Ming Chen, Wei-Chen Wang, Guangxuan Xiao, Xingyu Dang, Chuang Gan, Song Han For more info, please visit: AWQ website: hanlab.mit.edu/projects/awq Paper: arxiv.org/abs/230...

In this video, we introduce DistriFusion, a training-free algorithm to harness multiple GPUs to accelerate diffusion model inference without sacrificing image quality. It can reduce SDXL latency by up to 6.1× on 8 A100s. Our work has been accepted by CVPR 2024 as a highlight.

Condition-Aware Neural Network for Controlled Image Generation CVPR'24

github.com/mit-han-lab/efficientvit/tree/master/demo/gazesam

Hanrui Wang completed his PhD degree from MIT EECS in May 2024, advised by Prof. Song Han. He received his Bachelor of Engineering degree from Fudan University in 2018 and Master of Science degree from MIT in 2020. His research focuses on architecture and system-level supports for quantum computing, and AI for quantum. His work appears in conferences such as ISCA, MICRO, HPCA, QCE, DAC, ICCAD, ...

TinyML Demo on Microcontrollers (short)

AWQ and TinyChat: Activation-aware Weight Quantization for LLM Compression and Acceleration on Edge Device (Jetson Orin Nano) Large language models (LLMs) have shown excellent performance on various tasks, but the astronomical model size raises the hardware barrier for serving (memory size) and slows down token generation (memory bandwidth). In this paper, we pro- pose Activation-aware Weight Q...

This is the demo for our paper: On-Device Training Under 256KB Memory. We are transferring an ImageNet-pretrained model to the VWW dataset (person/no person) by updating the model within the tight memory budget.

Ji Lin completed his PhD degree from MIT EECS in December 2023, advised by Prof. Song Han. His research focuses on efficient deep learning computing for ML and accelerating large language models (LLMs). Ji is pioneering the research in the field of TinyML, including MCUNet, MCUNetV2, MCUNetV3 (on-device training), AMC, TSM (highlighted and integrated by NVIDIA), AnyCost GAN. Recently, he propos...

EfficientML.ai Lecture 23: Noise Robust Quantum ML (MIT 6.5940, Fall 2023, Zoom) Instructor: Hanrui Wang Slides: efficientml.ai

EfficientML.ai Lecture 23: Noise Robust Quantum ML (MIT 6.5940, Fall 2023) Instructor: Hanrui Wang Slides: efficientml.ai

EfficientML.ai Lecture 22: Quantum Machine Learning (MIT 6.5940, Fall 2023, Zoom) Instructor: Hanrui Wang Slides: efficientml.ai

EfficientML.ai Lecture 22: Quantum Machine Learning (MIT 6.5940, Fall 2023)

EfficientML.ai Lecture 21: Basics of Quantum Computing (MIT 6.5940, Fall 2023)

EfficientML.ai Lecture 21: Basics of Quantum Computing (MIT 6.5940, Fall 2023, Zoom)

EfficientML.ai Lecture 20: Efficient Fine-tuning and Prompt Engineering (MIT 6.5940, Fall 2023)

EfficientML.ai Lecture 20: Efficient Fine-tuning and Prompt Engineering (MIT 6.5940,Fall 2023,Zoom)

EfficientML.ai Lecture 19: On-Device Training and Transfer Learning (MIT 6.5940, Fall 2023)

EfficientML.ai Lecture 19: On-Device Training and Transfer Learning (MIT 6.5940, Fall 2023, Zoom)

MICRO'23 PockEngine: Sparse and Efficient Fine-tuning in a Pocket

EfficientML.ai Lecture 18: Distributed Training (Part II) (MIT 6.5940, Fall 2023, Zoom)

EfficientML.ai Lecture 18: Distributed Training (Part II) (MIT 6.5940, Fall 2023)

EfficientML.ai Lecture 17: Distributed Training (Part I) (MIT 6.5940, Fall 2023, Zoom)

EfficientML.ai Lecture 17: Distributed Training (Part I) (MIT 6.5940, Fall 2023)

EfficientML.ai Lecture 16 - Diffusion Model (MIT 6.5940, Fall 2023, Zoom)

EfficientML.ai Lecture 16 - Diffusion Model (MIT 6.5940, Fall 2023)

EfficientML.ai Lecture 15 - GAN, Video, and Point Cloud (MIT 6.5940, Fall 2023, Zoom)