Yuhao Ge

SDE @ Amazon AWS | MSCS @ UIUC | ex-SDE @ TikTok

geyuhao.jpg

I am an M.S. student in Computer Science at UIUC, working under Prof. Charith Mendis. My research interests span Machine Learning, Compilers, and LLM Efficiency. I interned at Amazon AWS, Annapurna Labs, where I focus on optimizing compilers to accelerate the training and inference of LLMs on Trainium, AWS’s custom-designed accelerator.

Previously, I earned dual B.S. degrees in Computer Engineering from Zhejiang University and the University of Illinois at Urbana-Champaign through their joint program. I also had the opportunity to be a visiting research student at the UCLA VAST Lab, under the supervision of Prof. Jason Cong, where I worked on FPGA accelerator design automation. Additionally, I have interned at TikTok and NFTGo.

🎉 news

Aug 09, 2024 🚀 I received a Certificate of Appreciation from the Neuron Compiler team at Amazon Annapurna Labs for developing autotuning infrastructure that significantly improved AWS Trainium performance. This project was recognized as one of the most impactful contributions during my internship.
May 20, 2024 I joined Amazon AWS, Annapurna Labs, as a software engineer intern. I am working with the Compiler team on the AWS Neuron, which aims to optimize deep learning training and inference on AWS Trainium and Inferentia chips.
May 13, 2023 I graduated from the University of Illinois at Urbana-Champaign (UIUC) with a bachelor’s degree in Computer Engineering, earning Highest Honors and Bronze Tablet recognition (top 3%).
Apr 29, 2023 I have finished a senior design project focused on SLAM-based navigation for autonomous vehicles, incorporating real-time 3D reconstruction of the surroundings. Check out the demo here.

💼 work

Amazon, Annapurna Labs
Software Engineer Intern 		2024.5 - 2024.8
NFTGo
Machine Learning Engineer Intern 		2023.2 - 2023.6
TikTok
Software Engineer Intern 		2022.5 - 2022.8

🎓 education

University of Illinois at Urbana-Champaign (UIUC)
M.S. in Computer Science 		2023.9 - 2025.5
University of California, Los Angeles (UCLA)
Visiting Student Researcher 		2022.5 - 2022.9
University of Illinois at Urbana-Champaign (UIUC)
B.S. in Computer Engineering 		2019.9 - 2023.5
Zhejiang University (ZJU)
B.S. in Computer Engineering 		2019.9 - 2023.5

📝 selected papers

  1. SPLAT
    splat.jpg
    SPLAT: A framework for optimised GPU code-generation for SParse reguLar ATtention
    Ahan Gupta, Yueming Yuan, Devansh Jain, Yuhao Ge, David Aponte, Yanqi Zhou, Charith Mendis
    We proposed a novel sparse format, ACSR, and a code-generation scheme, SPLAT, to achieve both generality and performance in diverse sparse-MHSA patterns on GPUs, resulting in significant speedups over Triton and TVM.
    Paper

📖 selected projects

  1. 3D Reconstruction
    senior_project.jpg
    Remote Car Control System with Real-time 3D Reconstruction
    Zhejiang University | 2023.1 - 2023.5
    Developed a Raspberry Pi-based robot car with remote control and realtime 3D-reconstruction, achieving a 10Hz framerate.
    PDF Video
  2. FPGA Optimization
    fpga.png
    Automated FPGA Accelerator Optimization
    University of California, Los Angeles | 2022.5 - 2022.11
    Working with Prof. Jason Cong’s group, researching Automated FPGA Accelerator Design. Combined GNN-based Cost Model with an ML/RL-based Design Space Exploration to achieve FPGA Accelerator Design Automation.
  3. FPGA Doodle Dump
    doodle.png
    Implement A Game Efficiently on the FPGA Board
    University of Illinois at Urbana-Champaign | 2021.9 - 2021.12
    Ported the game "Doodle Dump" to FPGA with SystemVerilog. Consumed only 400KB memory, 0.5w power to achieve a 50hz frame rate, won the Best Design Prize.
    Video

📷 extracurriculars

Drumming has been a consistent passion in my life, helping me maintain creativity and rhythm in everything I do. Checkout my video here.

latest posts

Jul 19, 2024 Hello World!