12 papers
From LLM Inference to Agentic Workloads: Characterization and Implications for Serving Systems
Chaokun Chang, Yukun Zhou, Kaihua Fu +10
Agentic applications are shifting AI serving from isolated model inference to long-running workloads in which LLMs coordinate tools, environments, and persistent state. However, th…
Tessera: Unlocking Heterogeneous GPUs through Kernel-Granularity Disaggregation
Tiancheng Hu, Jin Qin, Zheng Wang +10
Disaggregation maps parts of an AI workload to different types of GPUs, offering a path to utilize modern heterogeneous GPU clusters. However, existing solutions operate at a coars…
Silo-Bench: A Scalable Environment for Evaluating Distributed Coordination in Multi-Agent LLM Systems
Yuzhe Zhang, Feiran Liu, Yi Shan +8
Large language models are increasingly deployed in multi-agent systems to overcome context limitations by distributing information across agents. Yet whether agents can reliably co…
Huawei Cloud Model-as-a-Service on the CloudMatrix384 SuperPod
Ao Xiao, Bangzheng He, Baoquan Zhang +125
Scaled-out MoE LLMs and scaled-up SuperPods create new systems challenges for production Model-as-a-Service (MaaS), requiring disaggregation, low-latency communication, and decentr…
Efficient Serving of LLM Applications with Probabilistic Demand Modeling
Yifei Liu, Zuo Gan, Zhenghao Gan +8
Applications based on Large Language Models (LLMs) contains a series of tasks to address real-world problems with boosted capability, which have dynamic demand volumes on diverse b…
DDiT: Dynamic Resource Allocation for Diffusion Transformer Model Serving
Heyang Huang, Cunchen Hu, Jiaqi Zhu +7
The Text-to-Video (T2V) model aims to generate dynamic and expressive videos from textual prompts. The generation pipeline typically involves multiple modules, such as language enc…