About Chiyue Wei

Chiyue Wei is a Ph.D. student in Electrical and Computer Engineering at Duke University, working under the supervision of Professor Yiran Chen. His research interests lie at the intersection of computer architecture and deep learning. Prior to Duke, he earned his Bachelor’s degree in Electronic Engineering from Tsinghua University in 2023, where he conducted research with Professor Yuan Xie and Professor Yu Wang.

🔥 News

• [2026/06] 🚀 Excited to share our latest work on Diffusion LLM serving, Optimus: Elastic Decoding for Efficient Diffusion LLM Serving, delivering up to 6.1× throughput gain over autoregressive decoding. Check out the paper and code.
• [2026/05] 🎉 Excited to start my research internship in the AI-System Co-Design team at Meta, where I work on MTIA, Meta’s in-house AI accelerator.
• [2026/03] 🎉🎉 Our work EVA: Accelerating LLM Decoding via an Efficient Vector Quantization Architecture is accepted to ISCA 2026! Check out the paper and code.
• [2025/11] 🎉🎉 Two papers accepted to HPCA 2026! One of them features our work Focus: A Streaming Concentration Architecture for Efficient Vision-Language Models, now a 🏆 Best Paper Nominee! Check out the paper and code.
• [2025/08] Check out our work DPad, a training-free acceleration method for Diffusion LLMs, now available on on arXiv!
• [2025/08] Wrapped up my internship at NVIDIA, where I worked on the FlashInfer project. I developed high-performance and customizable attention kernels with CuTe DSL, optimized for Blackwell GPUs.
• [2025/06] Honored to be named a DAC 2025 Young Fellow.
• [2025/06] Excited that our works Phi, Transitive Array, and Ecco were presented at ISCA 2025, check out the slides for Phi.

• [2025/05] 🎉 I’m excited to start my summer internship at NVIDIA, focusing on LLM inference framework optimization within the Deep Learning Frameworks team.

• [2025/03] 🎉🎉🎉 Three papers accepted by ISCA 2025! Topics include acceleration for Spiking Neural Networks, General Matrix Multiplications, and Large Language Models.
• [2025/03] 🔥 I presents Prosperity at HPCA 2025 in Las Vegas! Check out presentation slides and video.
• [2024/11] 🎉 Our paper “Prosperity: Accelerating Spiking Neural Networks via Product Sparsity” is accepted by HPCA 2025.

📝 Selected Publications

• HPCA 2026 🏆 Best Paper Nominee Focus: A Streaming Concentration Architecture for Efficient Vision-Language Models, Chiyue Wei, Cong Guo, Junyao Zhang, Haoxuan Shan, Yifan Xu, Ziyue Zhang, Yudong Liu, Qinsi Wang, Changchun Zhou, Hai “Helen” Li, Yiran Chen

• Preprint Optimus: Elastic Decoding for Efficient Diffusion LLM Serving, Chiyue Wei, Cong Guo, Bowen Duan, Junyao Zhang, Haoxuan Shan, Yifei Wang, Yangjie Zhou, Hai “Helen” Li, Danyang Zhuo, Yiran Chen

• ISCA 2026 EVA: Accelerating LLM Decoding via an Efficient Vector Quantization Architecture, Bowen Duan, Cong Guo, Chiyue Wei, Haoxuan Shan, Yuzhe Fu, Xinhua Chen, Yifan Xu, Ziyue Zhang, Changchun Zhou, Hai Li, Yiran Chen

• ISCA 2025 Phi: Leveraging Pattern-based Hierarchical Sparsity for High-Efficiency Spiking Neural Networks, Chiyue Wei, Bowen Duan, Cong Guo, Jingyang Zhang, Qingyue Song, Hai Li, Yiran Chen

• ISCA 2025 Transitive Array: An Efficient GEMM Accelerator with Result Reuse, Cong Guo, Chiyue Wei, Jiaming Tang, Bowen Duan, Song Han, Hai Li, Yiran Chen

• ISCA 2025 Ecco: Improving Memory Bandwidth and Capacity for LLMs via Entropy-Aware Cache Compression, Feng Cheng, Cong Guo, Chiyue Wei, Junyao Zhang, Changchun Zhou, Edward Hanson, Jiaqi Zhang, Xiaoxiao Liu, Hai Li, Yiran Chen

• HPCA 2025 Prosperity: Accelerating Spiking Neural Networks via Product Sparsity, Chiyue Wei, Cong Guo, Feng Cheng, Shiyu Li, Hao Yang, Hai Li, Yiran Chen

• DATE 2023 CLAP: Locality Aware and Parallel Triangle Counting with Content Addressable Memory, Tianyu Fu, Chiyue Wei, Zhenhua Zhu, Shang Yang, Zhongming Yu, Guohao Dai, Huazhong Yang, Yu Wang

• ISCA 2022 DIMMining: Pruning-Efficient and Parallel Graph Mining on Near-Memory-Computing, Guohao Dai, Zhenhua Zhu, Tianyu Fu, Chiyue Wei, Bangyan Wang, Xiangyu Li, Yuan Xie, Huazhong Yang, Yu Wang