Kan Zhu
Scholar

Kan Zhu

Google Scholar ID: wkTiqicAAAAJ
University of Washington
Machine learning systemArchitecture
Google Scholar↗
Citations & Impact
All-time
Citations
473
 
H-index
5
 
i10-index
4
 
Publications
11
 
Co-authors
10
list available
Contact
No contact links provided.
Publications
6 items
Accelerating Large-Scale Reasoning Model Inference with Sparse Self-Speculative Decoding
2025
Cited
0
PolyServe: Efficient Multi-SLO Serving at Scale
2025
Cited
0
TeleRAG: Efficient Retrieval-Augmented Generation Inference with Lookahead Retrieval
2025
Cited
0
Tactic: Adaptive Sparse Attention with Clustering and Distribution Fitting for Long-Context LLMs
2025
Cited
0
NanoFlow: Towards Optimal Large Language Model Serving Throughput
arXiv.org · 2024
Cited
31
Fiddler: CPU-GPU Orchestration for Fast Inference of Mixture-of-Experts Models
arXiv.org · 2024
Cited
10
Resume (English only)
Co-authors
10 total
Baris Kasikci
Baris Kasikci
University of Washington
Yilong Zhao
Yilong Zhao
Ph.D. student, UC Berkeley
Chien-Yu Lin
Chien-Yu Lin
PhD Student, University of Washington
Arvind Krishnamurthy
Arvind Krishnamurthy
Short-Dooley Professor, Univ. of Washington
Zihao Ye
Zihao Ye
NVIDIA, University of Washington
Keisuke Kamahori
Keisuke Kamahori
University of Washington
Lequn Chen
Lequn Chen
University of Washington
Size Zheng
Size Zheng
ByteDance Seed