[Feature]: SLora hot loading

[Lexlum]

🚀 The feature, motivation and pitch

When S-lora starts, it needs to load both the base model and all the lora-heads simultaneously. Is there a way to add new LoRa adapters without interrupting the service of the base model and the existing lora-heads during its loading?

Alternatives

No response

Additional context

No response

Before submitting a new issue...

• [x] Make sure you already searched for relevant issues, and asked the chatbot living at the bottom right corner of the documentation page, which can answer lots of frequently asked questions.

[jeejeelee]

See: https://docs.vllm.ai/en/latest/features/lora.html#dynamically-serving-lora-adapters

[github-actions[bot]]

This issue has been automatically marked as stale because it has not had any activity within 90 days. It will be automatically closed if no further activity occurs within 30 days. Leave a comment if you feel this issue should remain open. Thank you!

[github-actions[bot]]

This issue has been automatically closed due to inactivity. Please feel free to reopen if you feel it is still relevant. Thank you!