feat(vllm): add structured output support via guided decoding

Update the vLLM backend to support structured output:
- Import GuidedDecodingParams from vllm.sampling_params
- Handle JSONSchema: parse and pass as GuidedDecodingParams(json_schema=...)
- Handle json_object response format: GuidedDecodingParams(json_object=True)
- Fall back to Grammar (GBNF) via GuidedDecodingParams(grammar=...)
- Remove phantom GuidedDecoding mapping (field doesn't exist in proto)
- Fix missing 'import time' and 'import json' for load_video and schema parsing

Priority: JSONSchema > json_object > Grammar (GBNF fallback)

Ref: #6857
Signed-off-by: eureka928 <meobius123@gmail.com>

backend/python/vllm/backend.py

@@ -2,6 +2,7 @@
 import asyncio
 from concurrent import futures
 import argparse
+import json
 import signal
 import sys
 import os
@@ -21,7 +22,7 @@ from grpc_auth import get_auth_interceptors
 
 from vllm.engine.arg_utils import AsyncEngineArgs
 from vllm.engine.async_llm_engine import AsyncLLMEngine
-from vllm.sampling_params import SamplingParams
+from vllm.sampling_params import SamplingParams, GuidedDecodingParams
 from vllm.utils import random_uuid
 from vllm.transformers_utils.tokenizer import get_tokenizer
 from vllm.multimodal.utils import fetch_image