-
Notifications
You must be signed in to change notification settings - Fork 27.5k
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
Tests: remove cuda versions when the result is the same 🧹🧹 #31955
Conversation
# Note on `EXPECTED_TEXT_COMPLETION`'s diff: the current value matches the original test if the original test | ||
# was changed to have a cache of 53 tokens (as opposed to 4096), on Ampere GPUs. |
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 comment was originally written by me in the equivalent llama test. It was probably copied around -- it does not apply here :)
The docs for this PR live here. All of your documentation changes will be reflected on that endpoint. The docs are available until 30 days after the last update. |
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.
Thanks for this tidy up 🧹 🧹 🧹 🧹
…ce#31955) remove cuda versions when the result is the same
…ce#31955) remove cuda versions when the result is the same
…ce#31955) remove cuda versions when the result is the same
remove cuda versions when the result is the same
What does this PR do?
Removes the dictionary of possible test outcomes for each cuda version, when ALL outcomes are exactly the same.
Why?