[BugFix] Use async Mistral Tokenizer in Chat Completions (#26134)

Signed-off-by: Ben Browning <bbrownin@redhat.com>
Co-authored-by: Cyrus Leung <tlleungac@connect.ust.hk>

tests/entrypoints/openai/test_serving_engine.py

@@ -0,0 +1,69 @@
+# SPDX-License-Identifier: Apache-2.0
+# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
+
+import asyncio
+import time
+from unittest.mock import Mock
+
+import pytest
+
+from vllm.config import ModelConfig
+from vllm.entrypoints.openai.serving_engine import OpenAIServing
+from vllm.entrypoints.openai.serving_models import OpenAIServingModels
+from vllm.transformers_utils.tokenizers.mistral import MistralTokenizer
+
+
+@pytest.fixture()
+def serving() -> OpenAIServing:
+    """Create a minimal OpenAIServing instance for testing."""
+
+    # Create minimal mocks
+    engine_client = Mock()
+    model_config = Mock(spec=ModelConfig)
+    model_config.max_model_len = 32768
+    models = Mock(spec=OpenAIServingModels)
+
+    serving = OpenAIServing(
+        engine_client=engine_client,
+        model_config=model_config,
+        models=models,
+        request_logger=None,
+    )
+    return serving
+
+
+@pytest.mark.asyncio
+async def test_async_mistral_tokenizer_does_not_block_event_loop(
+        serving: OpenAIServing):
+    expected_tokens = [1, 2, 3]
+
+    # Mock the blocking version to sleep
+    def mocked_apply_chat_template(*_args, **_kwargs):
+        time.sleep(2)
+        return expected_tokens
+
+    mock_tokenizer = Mock(spec=MistralTokenizer)
+    mock_tokenizer.apply_chat_template.side_effect = mocked_apply_chat_template
+
+    task = serving._apply_mistral_chat_template_async(tokenizer=mock_tokenizer,
+                                                      messages=[],
+                                                      chat_template=None,
+                                                      tools=[])
+
+    # Ensure the event loop is not blocked
+    blocked_count = 0
+    for _i in range(20):  # Check over ~2 seconds
+        start = time.perf_counter()
+        await asyncio.sleep(0)
+        elapsed = time.perf_counter() - start
+
+        # an overly generous elapsed time for slow machines
+        if elapsed >= 0.5:
+            blocked_count += 1
+
+        await asyncio.sleep(0.1)
+
+    # Ensure task completes
+    tokens = await task
+    assert tokens == expected_tokens, "Mocked blocking tokenizer was not called"
+    assert blocked_count == 0, ("Event loop blocked during tokenization")

vllm/entrypoints/openai/serving_engine.py

@@ -80,7 +80,7 @@ from vllm.sampling_params import BeamSearchParams, SamplingParams
 from vllm.tracing import (contains_trace_headers, extract_trace_headers,
                           log_tracing_disabled_warning)
 from vllm.transformers_utils.tokenizer import AnyTokenizer, MistralTokenizer
-from vllm.utils import (AsyncMicrobatchTokenizer, is_list_of,
+from vllm.utils import (AsyncMicrobatchTokenizer, is_list_of, make_async,
                         merge_async_iterators, random_uuid)
 
 logger = init_logger(__name__)
@@ -240,6 +240,8 @@ class OpenAIServing:
         self.enable_force_include_usage = enable_force_include_usage
 
         self._tokenizer_executor = ThreadPoolExecutor(max_workers=1)
+        self._apply_mistral_chat_template_async = make_async(
+            apply_mistral_chat_template, executor=self._tokenizer_executor)
 
         self._async_tokenizer_pool: dict[AnyTokenizer,
                                          AsyncMicrobatchTokenizer] = {}
@@ -798,7 +800,7 @@ class OpenAIServing:
         if tokenizer is None:
             request_prompt = "placeholder"
         elif isinstance(tokenizer, MistralTokenizer):
-            request_prompt = apply_mistral_chat_template(
+            request_prompt = await self._apply_mistral_chat_template_async(
                 tokenizer,
                 messages=messages,
                 **_chat_template_kwargs,