Motivation

Add a VS Code devcontainer configuration so the repository can be opened directly in a preconfigured development environment with GPU support and a writable mounted workspace.

Test

Test env: WSL2 Ubuntu 22.04 with RTX 4090

I followed S2-Pro example to test https://cookbook.sglang.io/omni/S2-Pro#22-install-sglang-omni-inside-docker

1. Opened project in vscode devcontainer
2. uv pip install -v ".[s2pro,dev]"
3. ./playground/tts/start.sh --model-path /models/s2-pro
4. Demo returns audio as expected

Modifications

• add .devcontainer/Dockerfile based on the existing frankleeeee/sglang-omni:dev image
• create a devuser that can adapt to host UID/GID collisions and preserve write access on the bind-mounted workspace
• install sudo, copy shell configuration, and expose uv on the user PATH
• add .devcontainer/devcontainer.json to build the dev target, mount the repo into /sgl-workspace/sglang-omni, enable --gpus all, set --shm-size 32g, and configure the Python VS Code extension

Related Issues

N/A

Accuracy Test

N/A. This change only adds development-container configuration and does not modify model-side code.

Benchmark & Profiling

N/A. This change is not expected to affect runtime performance.

Checklist

• Format your code according with pre-commit.
• Add unit tests.
• Update documentation / docstrings / example tutorials as needed.
• Provide throughput / latency benchmark results and accuracy evaluation results as needed.
• 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.