[Bugfix]: Fix final_res_batch list index out of range error (#21055)

Signed-off-by: chaunceyjiang <chaunceyjiang@gmail.com>

tests/v1/entrypoints/openai/test_completion.py

@@ -7,6 +7,7 @@ import openai  # use the official client for correctness check
 import pytest
 import pytest_asyncio
 import regex as re
+import requests
 from openai import BadRequestError
 
 from tests.utils import RemoteOpenAIServer
@@ -26,7 +27,8 @@ def default_server_args():
         "2048",
         "--max-num-seqs",
         "128",
-        "--enforce-eager"
+        "--enforce-eager",
+        "--enable-prompt-tokens-details",
     ]
 
 
@@ -679,3 +681,17 @@ async def test_invalid_grammar(client: openai.AsyncOpenAI, model_name: str):
             prompt=prompt,
             extra_body={"guided_grammar": invalid_simplified_sql_grammar},
         )
+
+
+@pytest.mark.asyncio
+async def test_completion_with_empty_prompt_embeds(
+        client: openai.AsyncOpenAI) -> None:
+    """Test completion with empty prompt embeds."""
+    payload: dict[str, list] = {"prompt_embeds": []}
+    headers: dict[str, str] = {"Content-Type": "application/json"}
+    # base_url = http://localhost:8000/v1/completions
+    response = requests.post(f"{client.base_url}completions",
+                             headers=headers,
+                             json=payload)
+    assert response.status_code == 200, (
+        f"Expected status code 200, got {response.status_code}. ")