[TEST]Add sending request with and without chat (#5286)

### What this PR does / why we need it?
This PR adds the method for sending chat and non-chat request, we need
it to test much folloing cases.

### Does this PR introduce _any_ user-facing change?
No

### How was this patch tested?
by running the test

- vLLM version: release/v0.13.0
- vLLM main:
ad32e3e19c

---------

Signed-off-by: jiangyunfan1 <jiangyunfan1@h-partners.com>

tests/e2e/nightly/features/test_qwen3_32b_int8_a3_feature_stack3.py

@@ -20,7 +20,7 @@ from vllm.utils.network_utils import get_open_port
 
 from tests.e2e.conftest import RemoteOpenAIServer
 from tools.aisbench import run_aisbench_cases
-from tools.send_request import send_text_request
+from tools.send_request import send_v1_chat_completions
 
 MODELS = [
     "vllm-ascend/Qwen3-32B-W8A8",
@@ -90,9 +90,9 @@ async def test_models(model: str, tp_size: int) -> None:
                             server_port=port,
                             env_dict=env_dict,
                             auto_port=False) as server:
-        send_text_request(prompts[0],
-                          model,
-                          server,
-                          request_args=api_keyword_args)
+        send_v1_chat_completions(prompts[0],
+                                 model,
+                                 server,
+                                 request_args=api_keyword_args)
         # aisbench test
         run_aisbench_cases(model, port, aisbench_cases)

tools/send_request.py

@@ -2,22 +2,36 @@ from typing import Any
 
 import requests
 
-data: dict[str, Any] = {
-    "messages": [{
-        "role": "user",
-        "content": "",
-    }],
-}
 
-
-def send_text_request(prompt, model, server, request_args=None):
-    data["messages"][0]["content"] = prompt
-    data["model"] = model
-    url = server.url_for("v1", "chat", "completions")
+def send_v1_completions(prompt, model, server, request_args=None):
+    data: dict[str, Any] = {"model": model, "prompt": prompt}
     if request_args:
         data.update(request_args)
+    url = server.url_for("v1", "completions")
     response = requests.post(url, json=data)
-    print("Status Code:", response.status_code)
+    print(f"Status Code: {response.status_code}")
     response_json = response.json()
-    print("Response:", response_json)
-    assert response_json["choices"][0]["message"]["content"], "empty response"
+    print(f"Response json: {response_json}")
+    response_text = response_json["choices"][0]["text"]
+    print(f"Response: {response_text}")
+    assert response_text, "empty response"
+
+
+def send_v1_chat_completions(prompt, model, server, request_args=None):
+    data: dict[str, Any] = {
+        "model": model,
+        "messages": [{
+            "role": "user",
+            "content": prompt,
+        }],
+    }
+    if request_args:
+        data.update(request_args)
+    url = server.url_for("v1", "chat", "completions")
+    response = requests.post(url, json=data)
+    print(f"Status Code: {response.status_code}")
+    response_json = response.json()
+    print(f"Response json: {response_json}")
+    response_text = response_json["choices"][0]["message"]["content"]
+    print(f"Response: {response_text}")
+    assert response_text, "empty response"