Fix structure output #1270
Merged
Fix structure output #1270
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
inkcherry
requested review from
kzawora-intel,
michalkuligowski,
mgawarkiewicz,
vivekgoe and
afierka-intel
as code owners
czhu15
reviewed
May 19, 2025
fixed |
czhu15
added a commit
that referenced
this pull request
May 20, 2025
Cherry-picked the fix from: #1270
czhu15
added a commit
that referenced
this pull request
May 20, 2025
Cherry-picked the fix from: #1270
czhu15
pushed a commit
that referenced
this pull request
May 25, 2025
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]>
HabanaAIUser
pushed a commit
that referenced
this pull request
Jul 2, 2025
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]>
jikunshang
pushed a commit
that referenced
this pull request
Jul 4, 2025
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 --------- Co-authored-by: root <[email protected]>
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.
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
cc @czhu15