Fix/async chat serving (#2727)

2024-05-03 20:04:14 +02:00
parent 7e65477e5e
commit f8e7adda21
5 changed files with 73 additions and 21 deletions
--- a/tests/entrypoints/test_openai_server.py
+++ b/tests/entrypoints/test_openai_server.py
@@ -150,7 +150,7 @@ def server(zephyr_lora_files):
    ray.shutdown()


-@pytest.fixture(scope="session")
+@pytest.fixture(scope="module")
 def client():
    client = openai.AsyncOpenAI(
        base_url="http://localhost:8000/v1",