Yaqi Xia

14 papers A* 1A 5B 2Journal 5Unranked 1
YearRankTypeTitle / Venue / Authors
2026 B conf
JanusQuant: Accurate and Efficient 2-bit KV Cache Quantization for Long-Context Inference.
PPoPP
Chengyu Sun, Yaqi Xia, Hulin Wang, Donglin Yang, Xiaobo Zhou, Dazhao Cheng
2025 B conf
Harnessing Inter-GPU Shared Memory for Seamless MoE Communication-Computation Fusion.
PPoPP
Hulin Wang, Yaqi Xia, Donglin Yang, Xiaobo Zhou, Dazhao Cheng
2025 J jnl
MPipeMoE: Memory Efficient MoE for Pre-trained Models with Adaptive Pipeline Parallelism.
CoRR
Zheng Zhang, Donglin Yang, Yaqi Xia, Liang Ding, Dacheng Tao, Xiaobo Zhou, Dazhao Cheng
2025 A conf
MXBLAS: Accelerating 8-bit Deep Learning with a Unified Micro-Scaled GEMM Library.
SC
Weihu Wang, Yaqi Xia, Donglin Yang, Xiaobo Zhou, Dazhao Cheng
2025 — conf
Voltrix: Sparse Matrix-Matrix Multiplication on Tensor Cores with Asynchronous and Balanced Kernel Optimization.
USENIX ATC
Yaqi Xia, Weihu Wang, Donglin Yang, Xiaobo Zhou, Dazhao Cheng
2024 A conf
Accelerating Distributed DLRM Training with Optimized TT Decomposition and Micro-Batching.
SC
Weihu Wang, Yaqi Xia, Donglin Yang, Xiaobo Zhou, Dazhao Cheng
2024 J jnl
MPMoE: Memory Efficient MoE for Pre-Trained Models With Adaptive Pipeline Parallelism.
IEEE Trans. Parallel Distributed Syst.
Zheng Zhang, Yaqi Xia, Hulin Wang, Donglin Yang, Chuang Hu, Xiaobo Zhou, Dazhao Cheng
2024 J jnl
Raptor-T: A Fused and Memory-Efficient Sparse Transformer for Long and Variable-Length Sequences.
IEEE Trans. Computers
Hulin Wang, Donglin Yang, Yaqi Xia, Zheng Zhang, Qigang Wang, Jianping Fan, Xiaobo Zhou, Dazhao Cheng
2024 J jnl
Redundancy-Free and Load-Balanced TGNN Training With Hierarchical Pipeline Parallelism.
IEEE Trans. Parallel Distributed Syst.
Yaqi Xia, Zheng Zhang, Donglin Yang, Chuang Hu, Xiaobo Zhou, Hongyang Chen, Qianlong Sang, Dazhao Cheng
2024 A conf
Scaling New Heights: Transformative Cross-GPU Sampling for Training Billion-Edge Graphs.
SC
Yaqi Xia, Donglin Yang, Xiaobo Zhou, Dazhao Cheng
2023 A conf
MPipeMoE: Memory Efficient MoE for Pre-trained Models with Adaptive Pipeline Parallelism.
IPDPS
Zheng Zhang, Donglin Yang, Yaqi Xia, Liang Ding, Dacheng Tao, Xiaobo Zhou, Dazhao Cheng
2023 A conf
Redundancy-Free High-Performance Dynamic GNN Training with Hierarchical Pipeline Parallelism.
HPDC
Yaqi Xia, Zheng Zhang, Hulin Wang, Donglin Yang, Xiaobo Zhou, Dazhao Cheng
2021 A* conf
ASFM-Net: Asymmetrical Siamese Feature Matching Network for Point Completion.
ACM Multimedia
Yaqi Xia, Yan Xia, Wei Li, Rui Song, Kailang Cao, Uwe Stilla
2021 J jnl
ASFM-Net: Asymmetrical Siamese Feature Matching Network for Point Completion.
CoRR
Yaqi Xia, Yan Xia, Wei Li, Rui Song, Kailang Cao, Uwe Stilla