[ci] Move 3 entrypoints tests to h200_35gb queue (#43164)

Signed-off-by: Simon Mo <simon@inferact.ai>
Signed-off-by: Simon Mo <simon@simon-mac-mini-9.local>
Co-authored-by: Simon Mo <simon@inferact.ai>
Co-authored-by: OpenAI Codex <noreply@openai.com>

.buildkite/test_areas/entrypoints.yaml

@@ -3,6 +3,7 @@ depends_on:
   - image-build
 steps:
 - label: Entrypoints Unit Tests
+  device: h200_35gb
   key: entrypoints-unit-tests
   timeout_in_minutes: 25
   working_dir: "/vllm-workspace/tests"
@@ -15,6 +16,7 @@ steps:
   - pytest -v -s entrypoints/weight_transfer
 
 - label: Entrypoints Integration (LLM)
+  device: h200_35gb
   key: entrypoints-integration-llm
   timeout_in_minutes: 60
   working_dir: "/vllm-workspace/tests"
@@ -114,6 +116,7 @@ steps:
       - image-build-amd
 
 - label: Entrypoints Integration (Responses API)
+  device: h200_35gb
   key: entrypoints-integration-responses-api
   timeout_in_minutes: 50
   working_dir: "/vllm-workspace/tests"

tests/entrypoints/openai/responses/test_parsable_context.py

@@ -68,7 +68,7 @@ async def client(server):
 async def test_basic(client: OpenAI, model_name: str):
     response = await client.responses.create(
         model=model_name,
-        input="What is 123 * 456?",
+        input="What is 123 * 456? Answer with only the number.",
         temperature=0.0,
     )
     assert response is not None