Ke Hong
Scholar

Ke Hong

Google Scholar ID: 134qQG4AAAAJ
Tsinghua University
efficient computingGPU accelerationsparse computingML system
Homepage↗Google Scholar↗
Citations & Impact
All-time
Citations
537
 
H-index
9
 
i10-index
9
 
Publications
18
 
Co-authors
9
list available
Contact
CVOpen ↗
Publications
7 items
db-SP: Accelerating Sparse Attention for Visual Generative Models with Dual-Balanced Sequence Parallelism
2025
Cited
0
Reducing Latency of LLM Search Agent via Speculation-based Algorithm-System Co-Design
2025
Cited
0
TASP: Topology-aware Sequence Parallelism
2025
Cited
0
PAROAttention: Pattern-Aware ReOrdering for Efficient Sparse and Quantized Attention in Visual Generation Models
2025
Cited
0
semi-PD: Towards Efficient LLM Serving via Phase-Wise Disaggregated Computation and Unified Storage
2025
Cited
0
FlashOverlap: A Lightweight Design for Efficiently Overlapping Communication and Computation
2025
Cited
0
MBQ: Modality-Balanced Quantization for Large Vision-Language Models
2024
Cited
0
Resume (English only)
Co-authors
9 total
Guohao Dai
Guohao Dai
Associate Professor of Shanghai Jiao Tong University
Yu Wang (汪玉)
Yu Wang (汪玉)
Department of Electronic Engineering, Tsinghua University, China
Xiuhong Li
Xiuhong Li
Infinigence-AI
Jiaming Xu
Jiaming Xu
Shanghai Jiao Tong University
Xuefei Ning
Xuefei Ning
Tsinghua University
Shiyao Li (李师尧)
Shiyao Li (李师尧)
Ph.D student, Tsinghua University
Tianyu Fu
Tianyu Fu
Ph.D at Tsinghua University
Xinhao Yang
Xinhao Yang
Tsinghua University