fix structured_output/guided_output for delayed_sampling #1494
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
1 if compute logits depend the sampling result , we fetch sample result
in advance.
2 if not, we keep its previous behavior to keep performance.
example:
```prompt = ("Generate a JSON with the brand, model and car_type of the most iconic car from the 90's") ```
use dalay_sampling with structure output
```
{
"brand": "Tuner's favorite Mitsubishi",
"model": "Mitsubishi Lancer Evolution VI",
"car_type": "Coupe"
}
```
cc @czhu15
---------
Co-authored-by: root <[email protected]>
inkcherry
requested review from
kzawora-intel,
madamczyk-intel,
michalkuligowski,
mgawarkiewicz-intel,
vivekgoe,
afierka-intel,
xuechendi,
jikunshang,
mswiniarsk and
PatrykWo
as code owners
|
/run-gaudi-tests |
|
please update the title, I think this PR is to fix structured_output/guided_output for delayed_sampling. Let's point that out in the title. |
xuechendi
approved these changes
Jul 2, 2025
inkcherry
changed the title
Thanks for pointing that out — I've added a more detailed explanation. |
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Outdated suggestions cannot be applied.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.
pick #1270
Under structured_output, Xgrammer needs to modify the logits, and there is a data dependency on the sampling results.
1 if compute logits depend the sampling result , we fetch sample result in advance.
2 if not, we keep its previous behavior to keep performance.
@czhu15