Research

Publications

The full list of my publications and preprints.

Publications

1. PPoPP ’27

   Plectra: Scheduling Parallelism for Diffusion Transformer

   Xinwei Qiang, Yifan Hu, Shixuan Sun, Jing Yang, Han Zhao, Chen Chen, Yu Feng, Jingwen Leng, Minyi Guo

   Paper Code
2. NeurIPS ’26

   AsymHP: Load-Balanced Sparse Attention for Video Diffusion Transformers

   Xinwei Qiang*, Yue Guan*, Ruihan Zhu, Mihir Jagtap, Zaifeng Pan, Zhongkai Yu, Chang Chen, Zhengding Hu, Yufei Ding, Adnan Aziz

   Paper Poster
3. ASPLOS ’27

   Impeller: Scalable and Efficient Zero-Knowledge Proof Computation Framework via Graph Compilation

   Liukun Yu*, Xinwei Qiang*, Shixuan Sun, Chen Chen, Jingwen Leng, Jin Dong

   Paper Code
4. SC ’26

   FluxZK: Scalable and Efficient Zero-Knowledge Proof Computation via GPU Acceleration

   Xinwei Qiang*, Liukun Yu*, Xiyu Wang, Zhengyi Li, Shixuan Sun, Jingwen Leng, Chen Chen, Jiaping Gui, Zhenzhe Zheng, Jin Dong, Minyi Guo

   Poster Code
5. ICML ’26

   TritonGym: A Benchmark for Agentic LLM Workflows in Triton GPU Code Generation

   Yue Guan*, Yichen Lin*, Xu Zhao, Jianzhu Yao, Xinwei Qiang, Zhongkai Yu, Pramod Viswanath, Yufei Ding, Adnan Aziz

   Paper Code Project
6. OSDI ’26

   Syncopate: Efficient Multi-GPU AI Kernels via Automatic Chunk-Centric Compute-Communication Overlap

   Xinwei Qiang*, Yue Guan*, Zhengding Hu, Keren Zhou, Yufei Ding, Adnan Aziz

   Paper Code
7. ICLR ’26

   DASH: Deterministic Attention Scheduling for High-Throughput Reproducible LLM Training

   Xinwei Qiang, Hongmin Chen, Shixuan Sun, Jingwen Leng, Xin Liu, Minyi Guo

   Paper Code
8. SOSP ’25

   Mercury: Unlocking Multi-GPU Operator Optimization for LLMs via Remote Memory Scheduling

   Yue Guan, Xinwei Qiang, Zaifeng Pan, Daniels Johnson, Yuanwei Fang, Keren Zhou, Yuke Wang, Wanlu Li, Yufei Ding, Adnan Aziz

   Paper Code

* Equal contribution.

Preprints

1. arXiv ’26

   Weights That Stay: On-Chip Megakernels for Serial Heads in Speculative Decoding

   Xinwei Qiang, Ziyi Xu, Zaifeng Pan, Chang Chen, Yufei Ding

   Paper Code Blog
2. arXiv ’26

   Understanding GPU Megakernels: Why Residency Can Mislead

   Xinwei Qiang, Ziyi Xu, Chang Chen, Zaifeng Pan, Zhongkai Yu, Yue Guan, Yufei Ding

   Paper Code Blog
3. arXiv ’26

   Zepp: Accelerating Distributed MoE Serving under Relaxed Balance Constraints

   Chang Chen, Andrew Yang, Tiancheng Chen, Jiangfei Duan, Xinwei Qiang, Zhongkai Yu, Xiang Fang, Yufei Ding

   Paper
4. arXiv ’26

   AgentReplay: Token-Wise Trace Replay Is Essential for Fair Serving System Performance Benchmarking

   Zaifeng Pan, Michael Wang, Chris Wu, Zhengding Hu, Xinwei Qiang, Zhongkai Yu, Yufei Ding

   Paper
5. arXiv ’26

   RR-Evict: Fine-Grained Prefix Cache Eviction beyond LRU for Agentic LLM Serving

   Zaifeng Pan, Chris Wu, Zhengding Hu, Xinwei Qiang, Zhongkai Yu, Yufei Ding

   Paper
6. arXiv ’26

   Argus: Orchestrating Cross-Layer GPU Performance Measurements around Semantic Regions

   Jianzhu Yao, Yue Guan, Srivatsan Ramesh, Yuanwei Fang, Jian Jiao, Boda Li, Yueming Hao, Xinwei Qiang, Pramod Viswanath, Yufei Ding, Bill Yoshimi, Alexey Loginov, Shane Nay, Adnan Aziz

   Paper
7. arXiv ’26

   Beyond Parallel Blindness: Information Floors and Model Gaps in Block Drafting

   Xinwei Qiang, Xiang Fang, Chang Chen, Zaifeng Pan, Yue Guan, Yufei Ding

   Paper Code Blog