support for ollama keep_alive parameter

[bogan-FMA]

Self Checks

• I have searched for existing issues search for existing issues, including closed ones.
• I confirm that I am using English to submit this report (我已阅读并同意 Language Policy).
• Pleas do not modify this template :) and fill in all the required fields.

1. Is this request related to a challenge you're experiencing?

yes

2. Describe the feature you'd like to see

support the keep_alive feature of ollama, detailed in ollama/ollama#2146

3. How will this feature improve your workflow or experience?

currently the model will unload after 5 min idle, the next reload will take more than 30min for a 70b model.

4. Additional context or comments

no

5. Can you help us with this feature?

• I am interested in contributing to this feature.