9 citations · 11 across the 12 of their papers we have counts for
13 papers
Weave: Fine-Grained Dynamic SM Scheduling in an MoE Megakernel for Compute-Communication Overlap
Ziyu Huang, Yangjie Zhou, Chenhao Zhu +15
Mixture-of-Experts (MoE) inference under expert parallelism (EP) turns each MoE layer into a distributed computation with costly dispatch and combine communication. State-of-the-ar…
Dissecting How Die Scaling Breaks GPU Fine-grained Scheduling
Xiaoze Fan, Jianhao Wang, Weihao Cui +8
Modern GPUs are no longer physically symmetric. Die scaling leads to both manufacturing-driven floorsweeping and cache and memory partitioning. The former creates chip-specific com…
PCR: A Prefetch-Enhanced Cache Reuse System for Low-Latency RAG Serving
Wenfeng Wang, Xiaofeng Hou, Peng Tang +5
Retrieval-Augmented Generation (RAG) systems enhance the performance of large language models (LLMs) by incorporating supplementary retrieved documents, enabling more accurate and…
MuxTune: Efficient Multi-Task LLM Fine-Tuning in Multi-Tenant Datacenters via Spatial-Temporal Backbone Multiplexing
Chunyu Xue, Yi Pan, Weihao Cui +4
Parameter-Efficient Fine-Tuning (PEFT) is widely applied as the backend of fine-tuning APIs for large language model (LLM) customization in datacenters. Service providers deploy se…
Specter: Fast MoE Inference via Quantization-Enabled Multi-Step Speculative Offloading
Wenfeng Wang, Jiacheng Liu, Xiaofeng Hou +7
Mixture-of-experts (MoE) models often exceed a single accelerator's memory capacity. Offloading experts to host memory creates a severe PCIe I/O bottleneck because data-dependent r…
MoE-Prism: Disentangling Monolithic Experts for Elastic MoE Services via Model-System Co-Designs
Xinfeng Xia, Xiaofeng Hou, Jiacheng Liu +5
Mixture-of-Experts (MoE) scales model capacity through sparse activation, and is becoming an important architecture for large language models (LLMs). However, existing MoE serving…
Boosting Embodied AI Agents through Perception-Generation Disaggregation and Asynchronous Pipeline Execution
Shulai Zhang, Ao Xu, Quan Chen +6
Embodied AI systems operate in dynamic environments, requiring seamless integration of perception and generation modules to process high-frequency input and output demands. Traditi…
Kairos: Low-latency Multi-Agent Serving with Shared LLMs and Excessive Loads in the Public Cloud
Jinyuan Chen, Jiuchen Shi, Quan Chen +1
Multi-agent applications utilize the advanced capabilities of large language models (LLMs) for intricate task completion through agent collaboration in a workflow. Under this situa…
Towards Resource-Efficient Serverless LLM Inference with SLINFER
Chuhao Xu, Zijun Li, Quan Chen +3
The rise of LLMs has driven demand for private serverless deployments, characterized by moderate-sized models and infrequent requests. While existing serverless solutions follow ex…
Survey of Disaggregated Memory: Cross-layer Technique Insights for Next-Generation Datacenters
Jing Wang, Chao Li, Taolei Wang +4
The growing scale of data requires efficient memory subsystems with large memory capacity and high memory performance. Disaggregated architecture has become a promising solution fo…
Efficient Function-as-a-Service for Large Language Models with TIDAL
Weihao Cui, Ziyi Xu, Han Zhao +4
Large Language Model (LLM) applications have emerged as a prominent use case for Function-as-a-Service (FaaS) due to their high computational demands and sporadic invocation patter…
A Survey on Inference Optimization Techniques for Mixture of Experts Models
Jiacheng Liu, Peng Tang, Wenfeng Wang +5
The emergence of large-scale Mixture of Experts (MoE) models represents a significant advancement in artificial intelligence, offering enhanced model capacity and computational eff…
HOBBIT: A Mixed Precision Expert Offloading System for Fast MoE Inference
Peng Tang, Jiacheng Liu, Xiaofeng Hou +5
The Mixture-of-Experts (MoE) architecture has demonstrated significant advantages in the era of Large Language Models (LLMs), offering enhanced capabilities with reduced inference…