In Gim

I am a second-year Ph.D. student in the Department of Computer Science at Yale University, where I work with Prof. Lin Zhong in the Efficient Computing Lab. I am interested in building efficient systems for generative AI through system design, formal methods, and prompt programming languages. Before starting my Ph.D. program at Yale, I received my B.S. degree from Yonsei University in Korea in 2021. Curriculum vitae.

Recent news

• 2024. 02. Prompt Cache is accepted to MLSys 2024!
• 2023. 12. We have submitted our work on a high-throughput LLM serving system. We will soon release the preprint and the code.
• 2023. 10. Our recent work on LLM prompt caching has been uploaded to arXiv.
• 2022. 08. Starting my academic journey at Yale.

Publications

• Scaling Language Model Serving with Multiplex Inference
  In Gim, Binghong (Leo) Li, Guojun Chen, Seung-Seob Lee, Nikhil Sarda, Anurag Khandelwal, and Lin Zhong
  in submission, December 2023 (preprint available on request)
• Prompt Cache: Modular Attention Reuse for Low-Latency Inference
  In Gim, Guojun Chen, Seung-Seob Lee, Nikhil Sarda, Anurag Khandelwal, and Lin Zhong
  MLSys 2024, May 2024 (pdf)
• Memory-Efficient DNN Training on Mobile Devices
  In Gim and JeongGil Ko
  MobiSys 2022, July 2022 (code, pdf)
• Fast Monte-Carlo Approximation of the Attention Mechanism
  Hyunjun Kim (In Gim) and JeongGil Ko
  AAAI 2022, January 2022 (code, pdf)