I’ll be on the job market in 2027. Happy to connect about opportunities!

Hello! I’m Zikun Li, a PhD candidate in the Computer Science Department at Carnegie Mellon University, advised by Prof. Zhihao Jia. My research focuses on making large language models more efficient, with interests in Efficient LLM Architectures, Efficient LLM Training and Inference Algorithms, and Reinforcement Learning. I received my bachelor’s degree in Computer Science from Peking University in 2021, where I worked with Prof. Tong Yang on algorithms for data stream mining.

News

14/09/2026 Our OpWeave preprint on flexible operator disaggregation for heterogeneous LLM serving is now available on arXiv. Check it out here!

23/08/2025 AdaServe is accepted by EuroSys ‘26! 🎊

23/01/2025 We release AdaServe, a system for high-throughput SLO-customized LLM serving with speculative decoding. Check it out here!

23/01/2025 TidalDecode is accepted by ICLR ‘25! 🎊

Publications

• [Preprint] OpWeave: Flexible Operator Disaggregation for Heterogeneous LLM Serving
  Zikun Li*, Yixuan Mei*, Shiqi Pan, Zixuan Chen, Xiaowen Zhang, Mengdi Wu, Shuhuai Lin, Yutong Yang, Zhihao Zhang, Xupeng Miao, Rashmi Vinayak and Zhihao Jia (* indicates equal contribution)

• [Preprint] Coral: Cost-Efficient Multi-LLM Serving over Heterogeneous Cloud GPUs
  Yixuan Mei, Zikun Li, Zixuan Chen, Shiqi Pan, Mengdi Wu, Xupeng Miao, Zhihao Jia and K. V. Rashmi

• [EuroSys ‘26] AdaServe: Accelerating Multi-SLO LLM Serving with SLO-Customized Speculative Decoding
  Zikun Li*, Zhuofu Chen*, Remi Delacourt, Gabriele Oliaro, Zeyu Wang, Qinghan Chen, Shuhuai Lin, April Yang, Zhihao Zhang, Zhuoming Chen, Sean Lai, Xinhao Cheng, Xupeng Miao and Zhihao Jia (* indicates equal contribution)

• [ICLR ‘25] TidalDecode: Fast and Accurate LLM Decoding with Position Persistent Sparse Attention
  Lijie Yang*, Zhihao Zhang*, Zhuofu Chen, Zikun Li and Zhihao Jia (* indicates equal contribution)

• [OOPSLA ‘24] Quarl: A Learning-Based Quantum Circuit Optimizer
  Zikun Li, Jinjun Peng, Yixuan Mei, Sina Lin, Yi Wu, Oded Padon and Zhihao Jia

• [PLDI ‘22] Quartz: superoptimization of Quantum circuits
  Mingkuan Xu, Zikun Li, Oded Padon, Sina Lin, Jessica Pointing, Auguste Hirth, Henry Ma, Jens Palsberg, Alex Aiken, Umut A Acar and Zhihao Jia

• [SIGMOD ‘21] BurstSketch: Finding Bursts in Data Streams
  Zheng Zhong*, Shen Yan*, Zikun Li*, Decheng Tan, Tong Yang and Bin Cui. (* indicates equal contribution)

• [SIGKDD ‘20] WavingSketch: An Unbiased and Generic Sketch for Finding Top-k Items in Data Streams
  Jizhou Li*, Zikun Li*, Yifei Xu*, Shiqi Jiang, Tong Yang, Bin Cui, Yafei Dai and Gong Zhang. (* indicates equal contribution)

Teaching

• TA of 15418/618 Parallel Computer Architecture and Programming, 2023 Fall

Miscellaneous

• I play 🎾 and 🎱 in my spare time.