6 citations · 15 across the 15 of their papers we have counts for
9 papers · 1 filter
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…
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…
DeepServe: Serverless Large Language Model Serving at Scale
Junhao Hu, Jiang Xu, Zhixia Liu +18
In this paper, we propose DEEPSERVE, a scalable and serverless AI platform designed to efficiently serve large language models (LLMs) at scale in cloud environments. DEEPSERVE addr…
BLITZSCALE: Fast and Live Large Model Autoscaling with O(1) Host Caching
Dingyan Zhang, Haotian Wang, Yang Liu +4
Model autoscaling is the key mechanism to achieve serverless model-as-a-service, but it faces a fundamental trade-off between scaling speed and storage/memory usage to cache parame…
MemServe: Context Caching for Disaggregated LLM Serving with Elastic Memory Pool
Cunchen Hu, Heyang Huang, Junhao Hu +8
Large language model (LLM) serving has transformed from stateless to stateful systems, utilizing techniques like context caching and disaggregated inference. These optimizations ex…
CaraServe: CPU-Assisted and Rank-Aware LoRA Serving for Generative LLM Inference
Suyi Li, Hanfeng Lu, Tianyuan Wu +6
Pre-trained large language models (LLMs) often need specialization for domain-specific tasks. Low-Rank Adaptation (LoRA) is a popular approach that adapts a base model to multiple…
Inference without Interference: Disaggregate LLM Inference for Mixed Downstream Workloads
Cunchen Hu, Heyang Huang, Liangliang Xu +9
Transformer-based large language model (LLM) inference serving is now the backbone of many cloud services. LLM inference consists of a prefill phase and a decode phase. However, ex…