Fix structured decoding and sampler #661
Merged
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
Signed-off-by: Chenyaaang <chenyangli@google.com>
DescriptionStart with a short description of what the PR does and how this is a change from The rest of the description includes relevant details and context, examples:
If the change fixes a bug or a Github issue, please include a link, e.g.,: TestsPlease describe how you tested this change, and include any instructions and/or ChecklistBefore submitting this PR, please make sure:
|
yaochengji
approved these changes
Sep 9, 2025
Collaborator
yaochengji
left a comment
yaochengji
left a comment
There was a problem hiding this comment.
LGTM, thanks for the fix!
py4
reviewed
Sep 9, 2025
| mask_index = scheduler_output.structured_output_request_ids.get( | ||
| req_id) | ||
| if mask_index is None: | ||
| sorted_struct_requests = sorted( |
Collaborator
There was a problem hiding this comment.
@Chenyaaang would be good to have a comment here what's happening here and below
utkarshsharma1
pushed a commit
that referenced
this pull request
Sep 14, 2025
Signed-off-by: Chenyaaang <chenyangli@google.com>
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Outdated suggestions cannot be applied.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.
Description
Fix TPU structured decoding and sampler
scheduler_output.grammar_bitmaskonly contains the entries for guided requests, sort the guided requests and use cumulative index to avoid index out of bound error.logits /= temperatureswill flip the result, causing error (e.g. result is !!!!!!!!, where ! refers to token 0).Tests
Checklist
Before submitting this PR, please make sure: