LLMVisor: A Real-Time Latency Attribution Model for Multi-Tenant LLM Serving
Shuowei Jin, Xueshen Liu, Jiaxin Shan, Le Xu, Tieying Zhang, Liguang Xie, Z. Morley Mao
cs.AI, cs.DC
Submitted: 2026-08-09
Updated: 2026-08-11
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- On the Opportunities and Risks of Foundation Models
- GPT-4o System Card
- Search-R1: Training LLMs to Reason and Leverage Search Engines with Reinforcement Learning
- Compute Or Load KV Cache? Why Not Both?
- Efficient Memory Management for Large Language Model Serving with PagedAttention
- AIBrix: Towards Scalable, Cost-Effective Large Language Model Inference Infrastructure
- HeterMoE: Efficient Training of Mixture-of-Experts Models on Heterogeneous GPUs
- RLBoost: Harvesting Preemptible Resources for Cost-Efficient Reinforcement Learning on LLMs
- LLM Inference Unveiled: Survey and Roofline Model Insights
- Eagle: Efficient Training-Free Router for Multi-LLM Inference
Related papers
- MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
- Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
- Agents' Last Exam
- The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
- MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
- Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems