[V1][Structured Output] Add apply_grammar_bitmask() method to model runner
#555
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
20 tasks
|
@wangxiyuan I have tested this, after this function added, structured output can work well. logs: Processed prompts: 100%|██████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 1/1 [00:02<00:00, 2.63s/it, est. speed input: 4.18 toks/s, output: 1.52 toks/s]
--------------------------------------------------
Guided decoding by Choice: Negative
--------------------------------------------------
Processed prompts: 100%|███████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 1/1 [00:00<00:00, 3.56it/s, est. speed input: 114.14 toks/s, output: 28.53 toks/s]
--------------------------------------------------
Guided decoding by Regex: alan_turing@enigma.com
--------------------------------------------------
Processed prompts: 100%|████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 1/1 [00:00<00:00, 1.25it/s, est. speed input: 27.60 toks/s, output: 27.60 toks/s]
--------------------------------------------------
Guided decoding by JSON: {"brand": "Toyota", "model": "Supra", "car_type": "Coupe"}
--------------------------------------------------
Processed prompts: 100%|████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 1/1 [00:00<00:00, 1.49it/s, est. speed input: 31.36 toks/s, output: 32.85 toks/s]
--------------------------------------------------
Guided decoding by Grammar: SELECT col_1 from table_1 where col_2 = 1 |
|
LGTM |
wangxiyuan
approved these changes
Apr 18, 2025
wangxiyuan
reviewed
Apr 18, 2025
|
|
||
| # We receive the structured output bitmask from the scheduler, but the | ||
| # indices of the requests in the batch may not match the indices of | ||
| # the bitmask since the scheduler doesn't know how the gpu runner is |
There was a problem hiding this comment.
OK, I will modify it later.
|
|
||
| # TODO: compatibility with spec decode. | ||
| # NOTE: | ||
| # 1. XGrammar bitmask applying only supports CPU and GPU. |
ttanzhiqiang
pushed a commit
to ttanzhiqiang/vllm-ascend
that referenced
this pull request
Apr 27, 2025
… runner (vllm-project#555) ### What this PR does / why we need it? Add `apply_grammar_bitmask()` method to model runner. This method is necessary for `xgrammar` structured output. --------- Signed-off-by: shen-shanshan <467638484@qq.com>
Angazenn
pushed a commit
to Angazenn/vllm-ascend
that referenced
this pull request
Oct 21, 2025
… runner (vllm-project#555) ### What this PR does / why we need it? Add `apply_grammar_bitmask()` method to model runner. This method is necessary for `xgrammar` structured output. --------- Signed-off-by: shen-shanshan <467638484@qq.com>
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
3 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 this PR does / why we need it?
Add
apply_grammar_bitmask()method to model runner.This method is necessary for
xgrammarstructured output.Does this PR introduce any user-facing change?
How was this patch tested?