ZZZili Zhang

Zili Zhang

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Zili Zhang has a total of 21 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Top Cited Papers
    Open Access

    RAGCache: Efficient Knowledge Caching for Retrieval-Augmented Generation

    by Chao Jin, Zili Zhang, Xuanlin Jiang, Fangyue Liu, Shufan Liu, Xuanzhe Liu, Xin Jin

    Retrieval-Augmented Generation (RAG) has demonstrated substantial advancements in various natural language processing tasks by integrating the strengths of large language models (LLMs) and external knowledge databases. However, the retrieval step introduces long sequence generation and extra data dependency, resulting in long end-to-end latency. Our analysis benchmarks current RAG systems and reveals that, while the retrieval step poses performance challenges, it also offers optimization opportunities through its retrieval pattern and streaming search behavior. We propose RAGCache, a latency-optimized serving system tailored for RAG. RAGCache leverages the retrieval pattern to organize and cache the intermediate states of retrieved knowledge in a knowledge tree across the GPU and host memory hierarchy, reducing LLM generation time. RAGCache employs dynamic speculative pipelining to exploit the streaming search behavior, overlapping retrieval with LLM generation to minimize end-to-end latency. We implement RAGCache based on vLLM and Faiss, and evaluate it on both open-source and production datasets. Experimental results demonstrate that RAGCache reduces the time to first token (TTFT) by up to 4× and improves the throughput by up to 2.1× compared to vLLM integrated with Faiss.


  • Open Access

    DistTrain: Addressing Model and Data Heterogeneity with Disaggregated Training for Multimodal Large Language Models

    by Zili Zhang, Yinmin Zhong, Yimin Jiang, Hanpeng Hu, Jianjian Sun, Zheng Ge, Yibo Zhu, Daxin Jiang, Xin Jin


  • Open Access

    Rise of Distributed Deep Learning Training in the Big Model Era: From a Software Engineering Perspective

    by Xuanzhe Liu, Diandian Gu, Zhenpeng Chen, Jinfeng Wen, Zili Zhang, Yun Ma, Haoyu Wang, Xin Jin

    Deep learning (DL) has become a key component of modern software. In the “ big model ” era, the rich features of DL-based software (i.e., DL software) substantially rely on powerful DL models, e.g., BERT, GPT-3, and the recently emerging GPT-4, which are trained on the powerful cloud with large datasets. Hence, training effective DL models has become a vital stage in the whole software lifecycle. When training deep learning models, especially those big models, developers need to parallelize and distribute the computation and memory resources amongst multiple devices (e.g., a cluster of GPUs) in the training process, which is known as distributed deep learning training , or distributed training for short. However, the unique challenges that developers encounter in distributed training process have not been studied in the software engineering community. Given the increasingly heavy dependence of current DL-based software on distributed training, this paper aims to fill in the knowledge gap and presents the first comprehensive study on developers’ issues in distributed training. To this end, we focus on popular DL frameworks that support distributed training (including TensorFlow, PyTorch, Keras, and Horovod) and analyze 1,131 real-world developers’ issues about using these frameworks reported on Stack Overflow and GitHub. We construct a fine-grained taxonomy consisting of 30 categories regarding the fault symptoms and summarize common fix patterns for different symptoms. We find that: (1) many distributed-specific faults and non-distributed-specific faults inherently share the same fault symptoms, making it challenging to debug; (2) most of the fault symptoms have frequent fix patterns; (3) about half of the faults are related to system-level configurations. Based on the results, we suggest actionable implications on research avenues that can potentially facilitate the distributed training to develop DL-based software, such as focusing on the frequent and common fix patterns when designing testing or debugging tools, developing efficient testing and debugging techniques for communication configuration along with the synthesis of network configuration analysis, designing new multi-device checkpoint-and-replay techniques to help reproduction, and designing serverless APIs for cloud platforms.


  • Open Access

    Ditto: Efficient Serverless Analytics with Elastic Parallelism

    by Chao Jin, Zili Zhang, Xingyu Xiang, Songyun Zou, Gang Huang, Xuanzhe Liu, Xin Jin