[Refactor] [1/N] to simplify the vLLM serving architecture (#28040)

Signed-off-by: chaunceyjiang <chaunceyjiang@gmail.com>
2025-12-03 17:26:39 +08:00
parent 69520bc695
commit 3f42b05fbc
27 changed files with 850 additions and 455 deletions
--- a/vllm/entrypoints/api_server.py
+++ b/vllm/entrypoints/api_server.py
@@ -118,6 +118,7 @@ async def init_app(
        )
    )
    app.state.engine_client = engine
+    app.state.args = args
    return app