会员服务
InfiniLoRA: Disaggregated Multi-LoRA Serving for Large Language Models
Arxiv
0+阅读 · 4月8日
Which Types of Heterogeneity Matter for Root Cause Localization in Microservice Systems ?
Arxiv
0+阅读 · 4月29日
Chimera: Latency- and Performance-Aware Multi-agent Serving for Heterogeneous LLMs
Arxiv
0+阅读 · 3月23日
Patterns behind Chaos: Forecasting Data Movement for Efficient Large-Scale MoE LLM Inference
Arxiv
0+阅读 · 4月2日
LegoDiffusion: Micro-Serving Text-to-Image Diffusion Workflows
Arxiv
0+阅读 · 4月9日
Scepsy: Serving Agentic Workflows Using Aggregate LLM Pipelines
Arxiv
0+阅读 · 4月16日
OServe: Accelerating LLM Serving via Spatial-Temporal Workload Orchestration
Arxiv
0+阅读 · 5月4日
Strait: Perceiving Priority and Interference in ML Inference Serving
Arxiv
0+阅读 · 4月30日
StreamWise: Serving Multi-Modal Generation in Real-Time at Scale
Arxiv
0+阅读 · 3月6日
CacheSolidarity: Preventing Prefix Caching Side Channels in Multi-tenant LLM Serving Systems
Arxiv
0+阅读 · 3月11日
Cornserve: A Distributed Serving System for Any-to-Any Multimodal Models
Arxiv
0+阅读 · 3月12日
Understanding the Issues, Their Causes and Solutions in Microservices Systems: An Empirical Study
Understanding the Issues, Their Causes and Solutions in Microservices Systems: An Empirical Study
Arxiv
0+阅读 · 2月19日
PAM: Processing Across Memory Hierarchy for Efficient KV-centric LLM Serving System
Arxiv
0+阅读 · 2月12日
Budgeting Discretion: Theory and Evidence on Street-Level Decision-Making
Arxiv
0+阅读 · 2月10日
When RL Meets Adaptive Speculative Training: A Unified Training-Serving System
Arxiv
0+阅读 · 2月6日
参考链接
微信扫码咨询专知VIP会员
Top