Jiazhi Jiang

28 papers A 4B 4C 2Journal 16Unranked 2
YearRankTypeTitle / Venue / Authors
2026 B conf
ASM-SpMM: Unleashing the Potential of Arm SME for Sparse Matrix Multiplication Acceleration.
PPoPP
Jiazhi Jiang, Xijia Yao, Jiayu Chen, Jinhui Wei, Dan Huang, Yutong Lu
2026 J jnl
Efficient KV Cache Spillover Management on Memory-Constrained GPU for LLM Inference.
IEEE Trans. Parallel Distributed Syst.
Jiazhi Jiang, Yao Chen, Zining Zhang, Bingsheng He, Pingyi Luo, Mian Lu, Yuqiang Chen, Hongbin Zhang, Jiangsu Du, Dan Huang, Yutong Lu
2025 J jnl
Co-Designing Transformer Architectures for Distributed Inference With Low Communication.
IEEE Trans. Parallel Distributed Syst.
Jiangsu Du, Yuanxin Wei, Shengyuan Ye, Jiazhi Jiang, Xu Chen, Dan Huang, Yutong Lu
2025 B conf
Doppeladler: Adaptive Tensor Parallelism for Latency-Critical LLM Deployment on CPU-GPU Integrated End-User Device.
PACT
Jiazhi Jiang, Xiao Liu, Jiangsu Du, Dan Huang, Yutong Lu
2025 C conf
Ghidorah: Fast LLM Inference on Edge with Speculative Decoding and Hetero-Core Parallelism.
ICCD
Jinhui Wei, Ye Huang, Yuhui Zhou, Jiazhi Jiang, Jiangsu Du
2025 J jnl
Ghidorah: Fast LLM Inference on Edge with Speculative Decoding and Hetero-Core Parallelism.
CoRR
Jinhui Wei, Ye Huang, Yuhui Zhou, Jiazhi Jiang, Jiangsu Du
2025 — conf
Oceanus: Enable SLO-Aware Vertical Autoscaling for Cloud-Native Streaming Services in Tencent.
SIGMOD Conference Companion
Zihao Chen, Jiazhi Jiang, Jiangang Liu, Chao Zhang, Yuqi Diao, Yang Li, Hanmei Luo, Peng Chen
2025 J jnl
PolyKAN: Efficient Fused GPU Operators for Polynomial Kolmogorov-Arnold Network Variants.
CoRR
Mingkun Yu, Heming Zhong, Dan Huang, Yutong Lu, Jiazhi Jiang
2025 J jnl
Resilience-Aware Elastic Scaling for Cloud-Native Online DL Training on Multi-Tenant GPU Clusters.
Proc. VLDB Endow.
Qianhao Wu, Jiazhi Jiang, Guihui Ling, Yue Pang
2025 J jnl
STEM: Efficient Relative Capability Evaluation of LLMs through Structured Transition Samples.
CoRR
Haiquan Hu, Jiazhi Jiang, Shiyou Xu, Ruhan Zeng, Tian Wang
2024 A conf
APTMoE: Affinity-Aware Pipeline Tuning for MoE Models on Bandwidth-Constrained GPU Nodes.
SC
Yuanxin Wei, Jiangsu Du, Jiazhi Jiang, Xiao Shi, Xianwei Zhang, Dan Huang, Nong Xiao, Yutong Lu
2024 A conf
Communication-Efficient Model Parallelism for Distributed In-Situ Transformer Inference.
DATE
Yuanxin Wei, Shengyuan Ye, Jiazhi Jiang, Xu Chen, Dan Huang, Jiangsu Du, Yutong Lu
2024 — conf
Efficient Coupling Streaming AI and Ensemble Simulations on HPC Clusters.
Euro-Par (1)
Jiazhi Jiang, Hongbin Zhang, Deyin Liu, Jiangsu Du, Xiaojiao Yao, Jinhui Wei, Pin Chen, Dan Huang, Yutong Lu
2024 J jnl
HTDcr: a job execution framework for high-throughput computing on supercomputers.
Sci. China Inf. Sci.
Jiazhi Jiang, Dan Huang, Hu Chen, Yutong Lu, Xiangke Liao
2024 B conf
Liger: Interleaving Intra- and Inter-Operator Parallelism for Distributed Large Model Inference.
PPoPP
Jiangsu Du, Jinhui Wei, Jiazhi Jiang, Shenggan Cheng, Dan Huang, Zhiguang Chen, Yutong Lu
2024 J jnl
SAIH: A Scalable Evaluation Methodology for Understanding AI Performance Trend on HPC Systems.
J. Comput. Sci. Technol.
Jiangsu Du, Dong-Sheng Li, Yingpeng Wen, Jiazhi Jiang, Dan Huang, Xiangke Liao, Yutong Lu
2024 J jnl
Sophisticated Orchestrating Concurrent DLRM Training on CPU/GPU Platform.
IEEE Trans. Parallel Distributed Syst.
Rui Tian, Jiazhi Jiang, Jiangsu Du, Dan Huang, Yutong Lu
2023 A conf
Accelerating Inference of 3D-CNN on ARMMany-core CPU via Hierarchical Model Partition.
DATE
Jiazhi Jiang, Zijiang Huang, Dan Huang, Jiangsu Du, Yutong Lu
2023 J jnl
Full-Stack Optimizing Transformer Inference on ARM Many-Core CPU.
IEEE Trans. Parallel Distributed Syst.
Jiazhi Jiang, Jiangsu Du, Dan Huang, Zhiguang Chen, Yutong Lu, Xiangke Liao
2023 J jnl
Hierarchical Model Parallelism for Optimizing Inference on Many-core Processor via Decoupled 3D-CNN Structure.
ACM Trans. Archit. Code Optim.
Jiazhi Jiang, Zijiang Huang, Dan Huang, Jiangsu Du, Lin Chen, Ziguang Chen, Yutong Lu
2023 J jnl
Improving Computation and Memory Efficiency for Real-world Transformer Inference on GPUs.
ACM Trans. Archit. Code Optim.
Jiangsu Du, Jiazhi Jiang, Jiang Zheng, Hongbin Zhang, Dan Huang, Yutong Lu
2023 C conf
MixRec: Orchestrating Concurrent Recommendation Model Training on CPU-GPU platform.
ICCD
Jiazhi Jiang, Rui Tian, Jiangsu Du, Dan Huang, Yutong Lu
2023 J jnl
Optimizing massively parallel sparse matrix computing on ARM many-core processor.
Parallel Comput.
Jiang Zheng, Jiazhi Jiang, Jiangsu Du, Dan Huang, Yutong Lu
2022 B conf
Characterizing and Optimizing Transformer Inference on ARM Many-core Processor.
ICPP
Jiazhi Jiang, Jiangsu Du, Dan Huang, Dongsheng Li, Jiang Zheng, Yutong Lu
2022 A conf
Handling heavy-tailed input of transformer inference on GPUs.
ICS
Jiangsu Du, Jiazhi Jiang, Yang You, Dan Huang, Yutong Lu
2022 J jnl
Optimizing small channel 3D convolution on GPU with tensor core.
Parallel Comput.
Jiazhi Jiang, Dan Huang, Jiangsu Du, Yutong Lu, Xiangke Liao
2022 J jnl
SAIH: A Scalable Evaluation Methodology for Understanding AI Performance Trend on HPC Systems.
CoRR
Jiangsu Du, Dongsheng Li, Yingpeng Wen, Jiazhi Jiang, Dan Huang, Xiangke Liao, Yutong Lu
2020 J jnl
A mechanism for scheduling multi robot intelligent warehouse system face with dynamic demand.
J. Intell. Manuf.
Zhi Li, Ali Vatankhah Barenji, Jiazhi Jiang, Ray Y. Zhong, Gangyan Xu