[Fix][Structured Output] using vocab_size to construct matcher (#14868)

Signed-off-by: Russell Bryant <rbryant@redhat.com>
Signed-off-by: Robert Shaw <114415538+robertgshaw2-redhat@users.noreply.github.com>
Signed-off-by: Aaron Pham <contact@aarnphm.xyz>
Co-authored-by: rshaw@neuralmagic.com <rshaw@neuralmagic.com>
Co-authored-by: Russell Bryant <rbryant@redhat.com>
Co-authored-by: Robert Shaw <114415538+robertgshaw2-redhat@users.noreply.github.com>
This commit is contained in:
Aaron Pham
2025-03-17 11:42:45 -04:00
committed by GitHub
co-authored by rshaw@neuralmagic.com <rshaw@neuralmagic.com> Russell Bryant Robert Shaw
parent aaaec52ad9
commit c0efdd655b
7 changed files with 70 additions and 85 deletions
@@ -1,5 +1,6 @@
# SPDX-License-Identifier: Apache-2.0
import json
import pickle
import pytest
@@ -208,8 +209,6 @@ def test_guided_decoding_backend_options():
def test_pickle_xgrammar_tokenizer_data():
# TODO: move to another test file for xgrammar
try:
import xgrammar as xgr
except ImportError:
@@ -217,7 +216,11 @@ def test_pickle_xgrammar_tokenizer_data():
from vllm.model_executor.guided_decoding.xgrammar_decoding import (
TokenizerData)
tokenizer_data = TokenizerData(vocab_type=xgr.VocabType.RAW)
tokenizer_data = TokenizerData(
metadata=
'{"vocab_type":2,"vocab_size":151665,"add_prefix_space":false,"stop_token_ids":[151645]}',
encoded_vocab=['!', '"', '#', '$', '%'],
)
pickled = pickle.dumps(tokenizer_data)
assert pickled is not None
@@ -225,4 +228,5 @@ def test_pickle_xgrammar_tokenizer_data():
depickled: TokenizerData = pickle.loads(pickled)
assert depickled is not None
assert depickled.vocab_type == xgr.VocabType.RAW
assert json.loads(
depickled.metadata)['vocab_type'] == xgr.VocabType.BYTE_LEVEL.value
@@ -18,9 +18,6 @@ MODELS_TO_TEST = [
"Qwen/Qwen2.5-1.5B-Instruct", "mistralai/Ministral-8B-Instruct-2410"
]
# Undo after https://github.com/vllm-project/vllm/pull/14868
pytest.skip(allow_module_level=True)
@pytest.mark.skip_global_cleanup
@pytest.mark.parametrize("guided_decoding_backend",