Skip to content
Research

Rocks, Pebbles and Sand: Modality-aware Scheduling for Multimodal Large Language Model Inference.

arXiv:2603.26498v3 Announce Type: replace-cross Abstract: Multimodal Large Language Models (MLLMs) power platforms like ChatGPT, Gemini, and Copilot, enabling rich interactions across text, images, and videos. Unlike text-only workloads, multimodal requests ar

arXiv cs.AIResearch source·