Qidong Su 蘇起冬

My first name is pronounced as /tɕʰi tʊŋ/.

I am a Computer Science PhD student in University of Toronto, advised by Gennady Pekhimenko. I got my bachelor degree from Shanghai Jiao Tong University (ACM Class).

My research focuses on accelerating programs on modern hardware. Currently I am optimizing inference speed of large-scale models.

I'm happy to discuss topics including (but not limited to) machine learning systems, compiler designs, parallel programming, etc.

An amateur in linguistics (phonetics, Chinese dialects, Japanese).

• [MLSys 2025] Seesaw: High-throughput LLM Inference via Model Re-sharding
  Qidong Su, Wei Zhao, Xin Li, Muralidhar Andoorveedu, Chenhao Jiang, Zhanda Zhu, Kevin Song, Christina Giannoula, Gennady Pekhimenko
  preprint
• [EuroSys 2025] Mist: Efficient Distributed Training of Large Language Models via Memory-Parallelism Co-Optimization
  Zhanda Zhu, Christina Giannoula, Muralidhar Andoorveedu, Qidong Su, Karttikeya Mangalam, Bojian Zheng, Gennady Pekhimenko
  preprint
• [PACT 2024] BOOM: Use your Desktop to Accurately Predict the Performance of Large Deep Neural Networks
  Qidong Su, Jiacheng Yang, Gennady Pekhimenko
  preprint paper
• [arXiv] APPL: A Prompt Programming Language for Harmonious Integration of Programs and Large Language Model Prompts
  Honghua Dong*, Qidong Su*, Yubo Gao, Zhaoyu Li, Yangjun Ruan, Gennady Pekhimenko, Chris J. Maddison, Xujie Si
  paper github
• [COLM 2024] A Survey on Deep Learning for Theorem Proving
  Zhaoyu Li, Jialiang Sun, Logan Murphy, Qidong Su, Zenan Li, Xian Zhang, Kaiyu Yang, Xujie Si
  paper
• [arXiv] The Synergy of Speculative Decoding and Batching in Serving Large Language Models
  Qidong Su, Christina Giannoula, Gennady Pekhimenko
  paper
• [APLAS 2023] TorchProbe: Fuzzing Dynamic Deep Learning Compilers
  Qidong Su, Chuqin Geng, Gennady Pekhimenko, Xujie Si
  paper
• [GNNSys 2021] Adaptive Load Balancing for Parallel GNN Training
  Qidong Su, Minjie Wang, Da Zheng, Zheng Zhang
  paper
• [IA³ 2021 @SC] DistDGL: Distributed Graph Neural Network Training for Billion-Scale Graphs
  Da Zheng, Chao Ma, Minjie Wang, Jinjing Zhou, Qidong Su, Xiang Song, Quan Gan, Zheng Zhang, George Karypis
  paper

• Email: qdsu ät cs.toronto.edu