[Bugfix] Offload blocking tokenizer ops to shared thread pool to unblock event loop (#34789)

Signed-off-by: Bvicii <yizhanhuang2002@gmail.com>
Co-authored-by: Cyrus Leung <tlleungac@connect.ust.hk>

tests/entrypoints/openai/completion/test_completion_error.py

@@ -54,6 +54,7 @@ class MockModelConfig:
     skip_tokenizer_init = False
     is_encoder_decoder: bool = False
     is_multimodal_model: bool = False
+    renderer_num_workers: int = 1
 
     def get_diff_sampling_param(self):
         return self.diff_sampling_param or {}