♨️ [GRPO] Fix potential hang in get_high_entropy_mask
#4041
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
akakakakakaa
changed the title
pramodith
reviewed
Sep 9, 2025
| pad_value = -1e9 | ||
|
|
||
| # Pad across processes so that every rank has the same tensor length | ||
| padded = self.accelerator.pad_across_processes(local, dim=0, pad_index=pad_value) |
Collaborator
There was a problem hiding this comment.
Very cool! Didn't know that function existed 😄
qgallouedec
changed the title
qgallouedec
changed the title
get_high_entropy_mask
|
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. |
qgallouedec
pushed a commit
that referenced
this pull request
Oct 2, 2025
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
4 participants
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Outdated suggestions cannot be applied.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.
What does this PR do?
Fixes #3933
Fix potential hang, If any rank hits non_pad_entropies.numel() == 0, the collective call will block forever:
Who can review?
@qgallouedec