Get started
Author

Weihao Cui

Observed names: Cui, Weihao, Weihao CUI
ORCID: 0000-0002-6646-5260
Observed ORCID: 0000-0002-6646-5260
OpenAlex ID: A5008837660
Enable simultaneous DNN services based on deterministic operator overlap and precise latency prediction
2021 · Weihao Cui, Han Zhao, et al. · International Conference for High Performance Computing, Networking, Storage and Analysis (SC) · 71
Laius
2019 · Wei Zhang, Weihao Cui, et al. · International Conference on Supercomputing · 48
Comet: Fine-grained Computation-communication Overlapping for Mixture-of-Experts
2025 · Zhang, Shulai, Zheng, Ningxin, et al. · arXiv (Cornell University) · 43
PDF
Tacker: Tensor-CUDA Core Kernel Fusion for Improving the GPU Utilization while Ensuring QoS
2022 · Han Zhao, Weihao Cui, et al. · IEEE International Symposium on High-Performance Computer Architecture (HPCA) · 43
Ebird: Elastic Batch for Improving Responsiveness and Throughput of Deep Learning Services
2019 · Weihao Cui, Mengze Wei, et al. · IEEE International Conference on Computer Design: VLSI in Computers and Processors (ICCD) · 34
Toward QoS-Awareness and Improved Utilization of Spatial Multitasking GPUs
2021 · Wei Zhang, Quan Chen, et al. · IEEE Transactions on Computers · 30
Improving GPU Sharing Performance through Adaptive Bubbleless Spatial-Temporal Sharing
2025 · Shulai Zhang, Quan Chen, et al. · European Conference on Computer Systems · 28
Exploiting Intra-SM Parallelism in GPUs via Persistent and Elastic Blocks
2021 · Han Zhao, Weihao Cui, et al. · IEEE International Conference on Computer Design: VLSI in Computers and Processors (ICCD) · 27
E2bird: Enhanced Elastic Batch for Improving Responsiveness and Throughput of Deep Learning Services
2020 · Weihao Cui, Quan Chen, et al. · IEEE Transactions on Parallel and Distributed Systems · 25
Towards High-Goodput LLM Serving with Prefill-decode Multiplexing
2026 · Yukang Chen, Weihao Cui, et al. · International Conference on Architectural Support for Programming Languages and Operating Systems (ASPLOS) · 24
Accelerating Sparse DNNs Based on Tiled GEMM
2024 · Cong Guo, Fengchen Xue, et al. · IEEE Transactions on Computers · 21
PDF
CODA: Improving Resource Utilization by Slimming and Co-locating DNN and CPU Jobs
2020 · Han Zhao, Weihao Cui, et al. · IEEE International Conference on Distributed Computing Systems (ICDCS) · 16
VQ-LLM: High-performance Code Generation for Vector Quantization Augmented LLM Inference
2025 · Zihan Liu, Xinhao Luo, et al. · IEEE International Symposium on High-Performance Computer Architecture (HPCA) · 13
PDF
Flare: Anomaly Diagnostics for Divergent LLM Training in GPU Clusters of Thousand-Plus Scale
2025 · Cui, Weihao, Zhang, Ji, et al. · arXiv (Cornell University) · 12
PDF
ISPA: Exploiting Intra-SM Parallelism in GPUs via Fine-Grained Resource Management
2022 · Han Zhao, Weihao Cui, et al. · IEEE Transactions on Computers · 11
PDF
Improving Cluster Utilization Through Adaptive Resource Management for Deep Neural Network and CPU Jobs Colocation
2023 · Han Zhao, Weihao Cui, et al. · IEEE Transactions on Computers · 8
Towards Fast Setup and High Throughput of GPU Serverless Computing
2024 · Zhao, Han, Cui, Weihao, et al. · arXiv (Cornell University) · 7
PDF
AdaptGear: Accelerating GNN Training via Adaptive Subgraph-Level Kernels on GPUs
2023 · Yangjie Zhou, Yaoxu Song, et al. · ACM International Conference on Computing Frontiers (CF) · 7
PDF
Maximizing the Utilization of GPUs Used by Cloud Gaming through Adaptive Co-location with Combo
2023 · Binghao Chen, Han Zhao, et al. · ACM Symposium on Cloud Computing (SoCC) · 6
PDF
PAME: precision-aware multi-exit DNN serving for reducing latencies of batched inferences
2022 · Shulai Zhang, Weihao Cui, et al. · International Conference on Supercomputing · 5
Arena: Efficiently Training Large Models via Dynamic Scheduling and Adaptive Parallelism Co-Design
2026 · Chunyu Xue, Weihao Cui, et al. · European Conference on Computer Systems · 4
A Sample-Free Compilation Framework for Efficient Dynamic Tensor Computation
2025 · Yangjie Zhou, Honglin Zhu, et al. · International Conference for High Performance Computing, Networking, Storage and Analysis (SC) · 4
Voyager: Input-Adaptive Algebraic Transformations for High-Performance Graph Neural Networks
2025 · Yangjie Zhou, Wenting Shen, et al. · International Conference on Architectural Support for Programming Languages and Operating Systems (ASPLOS) · 4
PDF
Taming Flexible Job Packing in Deep Learning Training Clusters
2025 · Pengyu Yang, Weihao Cui, et al. · ACM Transactions on Architecture and Code Optimization · 3
Adaptive Kernel Fusion for Improving the GPU Utilization While Ensuring QoS
2024 · Han Zhao, Junxiao Deng, et al. · IEEE Transactions on Computers · 3
Works count: 38
Citation count: 504
H-index: 13
I10-index: 15
Year
Topic
Type