My name is Bodun Hu (though I usually go by Edward). I'm a PhD student at UT Austin, majoring in Computer Science. I'm fortunately to be advised by Aditya Akella at UTNS lab.

My research lies at the intersection of machine learning, operating systems, and network. I love building systems for ML.

I got both a MS and BS in Computer Science from UT Austin. Before starting my PhD, I worked with Christopher Rossbach at SCEA lab, focsuing on GPU benchmarking and developing methods to enable OS kernel access to accelerators.

I have been very fortunate to intern with Theo Jepsen and Georgios Nikolaidis at Intel. I will be joining Meta's AI and Systems Co-design team as an intern this summer, where I will help build infrastructure to faciliate LLM training.

Contact: bodunhu at utexas.edu
PGP key: 76F092F8CD673517

Here’s the list of publications:

• Patchwork: A Unified Framework for RAG Serving, ArXiv
  Bodun Hu*, Luis Pabon*, Saurabh Agarwawl, Aditya Akella
• BlockLLM: Multi-tenant Finer-grained Serving for Large Language Models, ArXiv
  Bodun Hu, Jiamin Li, Le Xu, Myungjin Lee, Akshay Jajoo, Geon-Woo Kim, Hong Xu, Aditya Akella
• MOSEL: Inference Serving Using Dynamic Modality Selection, EMNLP 2024
  Bodun Hu, Le Xu, Jeongyoon Moon, Neeraja J. Yadwadkar, Aditya Akella
• FFN-SkipLLM: A Hidden Gem for Autoregressive Decoding with Adaptive Feed Forward Skipping, EMNLP 2024
  Ajay Jaiswal, Bodun Hu, Lu Yin, Yeonju Ro, Shiwei Liu, Tianlong Chen, Aditya Aeklla
• Towards a Machine Learning-Assisted Kernel with LAKE, ASPLOS 2023
  Henrique Fingler, Isha Tarte, Hangchen Yu, Ariel Szekely, Bodun Hu, Aditya Akella, Christopher J. Rossbach
• Altis: Modernizing GPGPU Benchmarks, ISPASS 2020
  Bodun Hu, Christopher J. Rossbach

Teaching:

• Fall 2024: CS 378 System For Machine Learning and Big Data
• Spring 2020: CS 378 Multicore Operating System Implementation

Service:

Reviewer: ACL 2025, ACL-SRW 2025