-
Notifications
You must be signed in to change notification settings - Fork 10.5k
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
server : tuning tests #7388
server : tuning tests #7388
Conversation
ggerganov
commented
May 19, 2024
•
edited
Loading
edited
- Fix incorrect passing of the temperature as the string "0.8f"
- Increase timeout to make the thread sanitizer workflow pass
- Pass temperature explicitly where it matters
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Ignore my previous comment, I had mixed up old and new.
72108cd
to
8ed8fa9
Compare
@@ -13,6 +13,7 @@ Feature: Results | |||
|
|||
Scenario Outline: consistent results with same seed | |||
Given <n_slots> slots | |||
And 0.0 temperature |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
This should be set to temperature 1, not temperature 0. With temperature 0 you get greedy decoding in which case the seed is irrelevant. So this test can no longer detect issues with e.g. the RNG state being shared between slots.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Ah yes, will push a fix now