publications

publications by categories in reversed chronological order. generated by jekyll-scholar.

2024

  1. exflow.png
    Exploiting Inter-Layer Expert Affinity for Accelerating Mixture-of-Experts Model Inference
    Jinghan Yao ,  Quentin Anthony ,  Aamir Shafi , and 2 more authors
    Advances in 38th IEEE International Parallel & Distributed Processing Symposium (IPDPS 24), 2024

2023

  1. flover.png
    Flover: A Temporal Fusion Framework for Efficient Autoregressive Model Parallel Inference
    Jinghan Yao ,  Nawras Alnaasan ,  Tian Chen , and 3 more authors
    Advances in 30th IEEE INTERNATIONAL CONFERENCE ON HIGH PERFORMANCE COMPUTING, DATA, & ANALYTICS (HiPC 23), 2023
  2. gvmi.png
    A novel framework for efficient offloading of communication operations to bluefield smartnics
    Kaushik Kandadi Suresh ,  Benjamin Michalowicz ,  Bharath Ramesh , and 6 more authors
    In 2023 IEEE International Parallel and Distributed Processing Symposium (IPDPS 23) , 2023
  3. xccl.png
    MPI-xCCL: A Portable MPI Library over Collective Communication Libraries for Various Accelerators
    Chen-Chun Chen ,  Kawthar Shafie Khorassani ,  Pouya Kousha , and 4 more authors
    In Proceedings of the SC’23 Workshops of The International Conference on High Performance Computing, Network, Storage, and Analysis , 2023

2021

  1. soft.png
    Soft: Softmax-free transformer with linear complexity
    Jiachen Lu ,  Jinghan Yao ,  Junge Zhang , and 6 more authors
    Advances in Neural Information Processing Systems (NeurIPS 21), 2021

2020

  1. sprnet.png
    SPRNet: single-pixel reconstruction for one-stage instance segmentation
    Jinghan Yao ,  Jun Yu ,  Jian Zhang , and 2 more authors
    IEEE transactions on cybernetics, 2020