[V0 deprecation] Guided decoding (#21347)

Signed-off-by: Reza Barazesh <rezabarazesh@meta.com>
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
Co-authored-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>

tests/entrypoints/openai/test_prompt_validation.py

@@ -9,6 +9,11 @@ import regex as re
 from ...utils import RemoteOpenAIServer
 
 
+@pytest.fixture(scope="function", autouse=True)
+def use_v1_only(monkeypatch):
+    monkeypatch.setenv('VLLM_USE_V1', '1')
+
+
 @pytest.mark.asyncio
 async def test_empty_prompt():
     model_name = "gpt2"
@@ -37,24 +42,3 @@ async def test_out_of_vocab_token_ids():
                                             prompt=[999999],
                                             max_tokens=5,
                                             temperature=0.0)
-
-
-@pytest.mark.asyncio
-async def test_reject_multistep_with_guided_decoding():
-    model_name = "gpt2"
-    server_args = ["--enforce-eager", "--num-scheduler-steps", "8"]
-    with RemoteOpenAIServer(model_name, server_args) as remote_server:
-        client = remote_server.get_async_client()
-
-        with pytest.raises(
-                openai.BadRequestError,
-                match=re.compile(
-                    '.*Guided decoding .* multi-step decoding.*').pattern):
-            await client.completions.create(
-                model=model_name,
-                prompt="Hello",
-                max_tokens=5,
-                temperature=0.0,
-                extra_body={"response_format": {
-                    "type": "json_object"
-                }})