Does vos_inference.py support multi-GPU running?

Thanks for the open source. I run vos_inference.py with my own video dataset on a machine with four v100 graphics cards (each with 32G memory). I detected that the program is only running on one card. Does vos_inference.py support multi-GPU running? How should I modify the code?

Start by reading vos_inference.py and tracing its inference entry point and device-selection logic. Determine whether the current script exposes or implements multi-GPU execution, then check the repository's inference examples for related usage. Done means the supported multi-GPU behavior and any required code changes are clearly established.

Written by the indexing model from the issue text.