All Stories

  1. From Prefix Cache to Fusion RAG Cache: Accelerating LLM Inference in Retrieval-Augmented Generation

    Article • Proceedings of the ACM on Management of Data, April 2026, ACM (Association for Computing Machinery)

    ZHANG Mingxing

  2. TrEnv-X: Transparently Share Serverless Execution Environments Across Different Functions and Nodes

    Article • ACM Transactions on Computer Systems, March 2026, ACM (Association for Computing Machinery)

    Teng Ma, Jinlei Jiang, ZHANG Mingxing

  3. Accelerating Stream Processing Engines via Hardware Offloading

    Article • Proceedings of the ACM on Management of Data, December 2025, ACM (Association for Computing Machinery)

    ZHANG Mingxing, Jinlei Jiang

  4. Mooncake: A KVCache-centric Disaggregated Architecture for LLM Serving

    Article • ACM Transactions on Storage, November 2025, ACM (Association for Computing Machinery)

    Teng Ma, ZHANG Mingxing

  5. KTransformers: Unleashing the Full Potential of CPU/GPU Hybrid Inference for MoE Models

    Article • October 2025, ACM (Association for Computing Machinery)

    Hongtao Chen, ZHANG Mingxing

  6. Scaling Up Memory Disaggregated Applications with SMART

    Article • April 2024, ACM (Association for Computing Machinery)

    ZHANG Mingxing

  7. Partial Failure Resilient Memory Management System for (CXL-based) Distributed Shared Memory

    Article • October 2023, ACM (Association for Computing Machinery)

    ZHANG Mingxing, Jinlei Jiang, Teng Ma

  8. Falcon: Fast OLTP Engine for Persistent Cache and Non-Volatile Memory

    Article • October 2023, ACM (Association for Computing Machinery)

    ZHANG Mingxing

  9. Efficiently Answering Path Queries on Evolving Graphs

    Article • January 2023, ACM (Association for Computing Machinery)

    Albert Zomaya, Ke Yang, ZHANG Mingxing, Hongtao Chen