Shang Yang

I am a second-year Ph.D. student at HAN LAB of MIT EECS, advised by Prof. Song Han. Before that, I received my Bachelor degree with highest honor from the Department of Electronic Engineering, Tsinghua University, China, where I was fortunate to be advised by Prof. Yu Wang.

My long-term goal is to build efficient machine learning systems for applications at different scales, especially the Large Language Models (LLMs). Recently, I am activately working on the efficient inference systems for LLMs/VLMs.

News

[2024/03] 🔥 We have released an updated version of TinyChat. Visual Language Models (e.g. VILA) are supported! Play with our demo!
[2024/02] 🔥 AWQ is accepted by MLSys 2024!
[2023/10] 🔥 I presented TorchSparse++ at MICRO 2023! See the video and slides here!

Selected Publications

arXiv

QServe: W4A8KV4 Quantization and System Co-design for Efficient LLM Serving

Yujun Lin*, Haotian Tang*, Shang Yang*, Zhekai Zhang, Guangxuan Xiao, Chuang Gan, Song Han.

arXiv, 2024.

Code

MLSys

AWQ: Activation-aware Weight Quantization for On-Device LLM Compression and Acceleration

Ji Lin*, Jiaming Tang*, Haotian Tang†, Shang Yang†, Wei-Ming Chen, Wei-Chen Wang, Guangxuan Xiao, Xingyu Dang, Chuang Gan, Song Han.

The Seventh Annual Conference on Machine Learning and Systems (MLSys), 2024.

Code Best Paper Award

MICRO

TorchSparse++: Efficient Training and Inference Framework for Sparse Convolution on GPUs

Haotian Tang*, Shang Yang*, Zhijian Liu, Ke Hong, Zhongming Yu, Xiuyu Li, Guohao Dai, Yu Wang, Song Han.

56th IEEE/ACM International Symposium on Microarchitecture (MICRO), 2023.

Code

DAC

Heuristic Adaptability to Input Dynamics for SpMM on GPUs

Guohao Dai, Guyue Huang, Shang Yang, Zhongming Yu, Hengrui Zhang, Yufei Ding, Yuan Xie, Huazhong Yang, Yu Wang.

59th Design Automation Conference (DAC), 2022.

Best Paper Award Nominee

Blogs

TinyChat: Large Language Model on the Edge

Running large language models (LLMs) on the edge is of great importance. In this blog, we introduce TinyChat, an efficient and lightweight system for LLM deployment on the edge. It runs Meta's latest LLaMA-2 model at 30 tokens / second on NVIDIA Jetson Orin and can easily support different models and hardware.

Code

TinyChat: Visual Language Models & Edge AI 2.0

Explore the latest advancement in TinyChat and AWQ - the integration of Visual Language Models (VLM) on the edge! The exciting advancements in VLM allows LLMs to comprehend visual inputs, enabling seamless image understanding tasks like caption generation, question answering, and more. With the latest release, TinyChat now supports leading VLMs such as VILA, which can be easily quantized with AWQ, empowering users with seamless experience for image understanding tasks.

Code