wassname/vllm
1
0
Fork 0
mirror of https://github.com/wassname/vllm.git synced 2026-09-12 13:01:01 +08:00
Code Issues Packages Projects Releases Wiki Activity

Fix/async chat serving (#2727)

Browse Source
This commit is contained in:
Sebastian Schoennenbeck
2024-05-03 11:04:14 -07:00
committed by GitHub
parent 7e65477e5e
commit f8e7adda21
5 changed files with 73 additions and 21 deletions
Download Patch File Download Diff File Expand all files Collapse all files
tests/entrypoints/test_openai_server.py
+1 -1
View File
@@ -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",