Respond with JSON if the request is non-stream

[aponcedeleonch]

We are currently not handling non-streaming requests, e.g.

% curl -SsX POST "http://localhost:8989/vllm/chat/completions" \
     -H "Content-Type: application/json" \
     -H "Authorization: Bearer $token" \
     -d '{
           "model": "Qwen/Qwen2.5-Coder-14B-Instruct",
           "messages": [{"role": "user", "content": "hello."}],
           "stream": false
        }'

This PR enables to respons with the entire JSON if the request was non-streaming.

Before PR response:

data: 'async for' requires an object with __aiter__ method, got ModelResponse

data: [DONE]

After this PR:

{
  "id": "chatcmpl-AZyYAAOFMsHdx2rabESYcHjsObIB2",
  "created": 1733137598,
  "model": "gpt-4o-mini-2024-07-18",
  "object": "chat.completion",
  "system_fingerprint": "fp_0705bf87c0",
  "choices": [
    {
      "finish_reason": "stop",
      "index": 0,
      "message": {
        "content": "Hello! How can I assist you today?",
        "role": "assistant",
        "tool_calls": null,
        "function_call": null
      }
    }
  ],
  "usage": {
    "completion_tokens": 9,
    "prompt_tokens": 9,
    "total_tokens": 18,
    "completion_tokens_details": {
      "accepted_prediction_tokens": 0,
      "audio_tokens": 0,
      "reasoning_tokens": 0,
      "rejected_prediction_tokens": 0
    },
    "prompt_tokens_details": {
      "audio_tokens": 0,
      "cached_tokens": 0
    }
  },
  "service_tier": null
}