[Usage]: Is there a way to make the results of two different calls to VLLM with temperature > 0 consistent?

[Some-random]

Your current environment

The output of `python collect_env.py`

How would you like to use vllm

I know that setting the temperature to 0 ensures that the results of two different calls with the same input will be identical. Is there a way to ensure consistent results when the input is different, perhaps by using a seed?

[devdev999]

Yes, add the seed as part of your params.

[Some-random]

Hi @devdev999, thanks for your reply! However, I've tried setting seed but it's not working

[Some-random]

Is there an update on this issue?

[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!