[nvbug 5333996 ][fix] Unload XQA cubins early to avoid static lifetime #5133
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Previously they were incorrectly managed by a static variable. So unloading could happen after cuda context destroy and can cause problems. This change use observer to manage them, and unload happens when the last user is destroyed. Also switch to context-less loading APIs, so it's safe to switch cuda context for users. Signed-off-by: Yao Yao <[email protected]>
|
/bot run |
|
PR_Github #8515 [ run ] triggered by Bot |
|
PR_Github #8515 [ run ] completed with state |
ming-wei
approved these changes
Jun 12, 2025
|
/bot run |
|
PR_Github #8604 [ run ] triggered by Bot |
|
/bot run |
|
PR_Github #8667 [ run ] triggered by Bot |
|
PR_Github #8667 [ run ] completed with state |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Previously they were incorrectly managed by a static variable. So unloading could happen after cuda context destroy and can cause problems. This change use observer to manage them, and unload happens when the last user is destroyed.
Also switch to context-less loading APIs, so it's safe to switch cuda context for users.