Rapid-MLX Model Provider
raullenchai/rapid-mlx-dsh-provider · skills
Native Rapid-MLX provider for DeepSeek Harness (dsh) — dsh reads model facts from the server instead of your settings.yaml.
★ 71GitHub stars
19Forks
2026-08-22Last updated
JavaScriptLanguage
Apache-2.0License
Key features
- DSH can already talk to a local Rapid-MLX server through its generic openai-completions provider.
- Installs and activates as a profile layer (no "declares no dsh.bundle" warning
- recommended_sampling — should be applied automatically per model.
- If you start reading a new /v1/models field here, add it there too.
- That route works — but it knows nothing about your model beyond what you hand-wrote
Install command
dsh plugin --profile web add github:raullenchai/rapid-mlx-dsh-provider