Scholar
Qianchao Zhu
Google Scholar ID: S0I30-gAAAAJ
peking university
High Performance Computing
Machine Learning System
Follow
Google Scholar
↗
Citations & Impact
All-time
Citations
136
H-index
4
i10-index
3
Publications
10
Co-authors
0
Publications
6 items
UltraEP: Unleash MoE Training and Inference on Rack-Scale Nodes with Near-Optimal Load Balancing
2026
Cited
0
PROBE: Co-Balancing Computation and Communication in MoE Inference via Real-Time Predictive Prefetching
2026
Cited
0
SlimPack: Fine-Grained Asymmetric Packing for Balanced and Efficient Variable-Length LLM Training
2025
Cited
0
Zeppelin: Balancing Variable-length Workloads in Data Parallel Large Model Training
2025
Cited
0
HeteroSpec: Leveraging Contextual Heterogeneity for Efficient Speculative Decoding
2025
Cited
0
SampleAttention: Near-Lossless Acceleration of Long Context LLM Inference with Adaptive Structured Sparse Attention
arXiv.org · 2024
Cited
22
