Serving | JJ's Blog

📝 Empower Vision Applications with LoRA LMM - Eurosys'25

📝 Elastic On-Device LLM Service - MobiCom '25

📝 RServe: Overlapping Encoding and Prefill for Efficient LMM Inference

📝 Jupiter: Fast and Resource-Efficient Collaborative Inference of Generative LLMs on Edge Devices - INFOCOM'25

📝 Efficiently Serving Large Multimodal Models Using EPD Disaggregation - ICML'25

📝 ElasticMM: Efficient Multimodal LLMs Serving with Elastic Multimodal Parallelism - NeurIPS'25 Oral