Motivation

Currently, the device argument in ServerArgs defaults to "cuda", which forces the use of CUDA even when other hardware accelerators (like XPU, HPU, or CPU) may be available or preferred. This PR aims to make the device selection more dynamic and flexible by automatically detecting the available device when no explicit device is specified.

Modifications

Changed device default from "cuda" to None
If device is not specified, get_device() will automatically detect and set the appropriate device (cuda, xpu, hpu).

Checklist

• Format your code according to the Code Formatting with Pre-Commit.
• Add unit tests as outlined in the Running Unit Tests.
• Update documentation / docstrings / example tutorials as needed, according to Writing Documentation.
• Provide throughput / latency benchmark results and accuracy evaluation results as needed, according to Benchmark and Profiling and Accuracy Results.
• For reviewers: If you haven't made any contributions to this PR and are only assisting with merging the main branch, please remove yourself as a co-author when merging the PR.
• Please feel free to join our Slack channel at https://slack.sglang.ai to discuss your PR.