Make AsyncLLMEngine more robust & fix batched abort (#969)

Signed-off-by: Antoni Baum <antoni.baum@protonmail.com> Co-authored-by: Avnish Narayan <38871737+avnishn@users.noreply.github.com>
2023-09-07 13:43:45 -07:00
parent 7a9c20c715
commit c07ece5ca4
7 changed files with 345 additions and 55 deletions
--- a/vllm/entrypoints/openai/api_server.py
+++ b/vllm/entrypoints/openai/api_server.py
@@ -44,6 +44,7 @@ TIMEOUT_KEEP_ALIVE = 5  # seconds
 logger = init_logger(__name__)
 served_model = None
 app = fastapi.FastAPI()
+engine = None


 def create_error_response(status_code: HTTPStatus,