Hi, I'm Ahan Gupta, a computer science PhD student at UIUC. Broadly, I investigate high-performance machine learning from the perspective of compilers/systems and algorithms. Check out my publications for my latest work.
In the not so distant past, I have worked as a researcher at Google DeepMind (Mountain View 2024), as well as a software engineer at Citadel (Hong Kong 2021) and Ninja-van (Singapore 2018). For more information, feel free to look at my cv.
A (relatively) up to date list of my publications.
Ahan Gupta, Yueming Yuan, Devansh Jain, Yuhao Ge, David Aponte, Yanqi Zhou, Charith Mendis. SPLAT: A framework for optimised GPU code-generation for SParse reguLar ATtention. OOPSLA 2025.
Hoa La*, Ahan Gupta*, Alex Morehead, Jianlin Cheng, Minjia Zhang. MegaFold: System-Level Optimizations for Accelerating Protein Structure Prediction Models. In Submission.
Yueming Yuan, Ahan Gupta, Jianping Li, Sajal Dash, Feiyi Wang, Minjia Zhang. X-MoE: Enabling Scalable Training for Emerging Mixture-of-Experts Architectures on HPC Platforms. In submission.
Muyan Hu, Ahan Gupta, Jiachen Yuan, Vima Gupta, Xin Xu, Janardhan Kulkarn, Ofer Dekel, Vikram Adve, Charith Mendis. VTC: DNN Compilation with Virtual Tensors for Data Movement Elimination. In submission.
Ahan Gupta, Hao Guo, Yueming Yuan, Yanqi Zhou, Charith Mendis. FLuRKA: Fast fused Low-Rank & Kernel Attention. In Submission.
* Denotes equal contribution.