DistMLLM: Enhancing Multimodal Large Language Model Serving in Heterogeneous Edge Computing
Xingyu Yuan, Hui Chen, Lei Liu, He Li, Charith Perera · 2025
Read DistMLLM: Enhancing Multimodal Large Language Model Serving in Heterogeneous Edge Computing by Xingyu Yuan, Hui Chen, Lei Liu, He Li, Charith Perera (2025) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/pmc-12737198.txt.
Description
Xingyu Yuan and co-authors designed in 2025 a system for serving giant multimodal AI models on scattered edge devices. Such models read text, pictures, and sound together but demand heavy computing that small, mixed edge hardware struggles to supply. Their framework splits each job into an encoding stage and a thinking stage.
Different devices take the stage they handle best. A learning scheduler, built from competing software agents, assigns work while device conditions shift and providers chase profit. Simulations show steadier long-run earnings than rival layouts. The design suits smart cameras and local assistants that cannot wait for distant data centers.
Catalog record
| CREATOR | Xingyu Yuan, Hui Chen, Lei Liu, He Li, Charith Perera |
|---|---|
| YEAR | 2025 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 42 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |