-
Notifications
You must be signed in to change notification settings - Fork 181
Ensure all bindings have GIL released #768
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
Conversation
/ok to test 67a8837 |
/ok to test e21dee5 |
This comment has been minimized.
This comment has been minimized.
/ok to test 79d2461 |
/ok to test 5eb1fee |
@@ -243,7 +243,7 @@ Enable device code optimization. When specified along with ``-G``\ , enables lim | |||
|
|||
- ``--Ofast-compile={0|min|mid|max}``\ (``-Ofc``\ ) | |||
|
|||
Specify level to prefer device code compilation speed, where 'max' focuses only on the fastest compilation speed, 'mid' balances compile time and runtime, 'min' has a more minimal impact on both, and 0 (default) is normal compilation | |||
Specify the fast-compile level for device code, which controls the tradeoff between compilation speed and runtime performance by disabling certain optimizations at varying levels. |
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.
Pinged offline regarding this being incorrectly generated
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.
Discussed offline, this change is coming from CUDA 12.9.1 header (which mismatches with the public NVRTC 12.9.1 documentation). The description looks incomplete because of #770, which is a generic issue to all APIs that have inner lists in the docs, not unique to just this option.
|
Description
closes #624
Checklist