A high-throughput and memory-efficient inference and serving engine for LLMs
Mirrored from https://github.com/tduncan-lum/Nvidia-Optimization-Stack---VLLM.git
Synced Nov 5, 03:30 UTC
[BugFix] KeyError on scope["method"] for realtime api websocket in AuthenticationMiddleware (#36934)
Signed-off-by: daniebrill <50454544+daniebrill@users.noreply.github.com> Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
daniebrill committed
Apr 15, 2026 at 18:15 UTC
f2145efcb6dc7b5ff0ec0a321508ec7f313c6f83
1 file changed
+4
-1
vllm/entrypoints/openai/server_utils.py
+4
-1
@@ -69,7 +69,10 @@ class AuthenticationMiddleware:
69
return token_match
70
71
def __call__(self, scope: Scope, receive: Receive, send: Send) -> Awaitable[None]:
72
- if scope["type"] not in ("http", "websocket") or scope["method"] == "OPTIONS":
72
+ if (
73
+ scope["type"] not in ("http", "websocket")
74
+ or scope.get("method") == "OPTIONS"
75
+ ):
76
# scope["type"] can be "lifespan" or "startup" for example,
77
# in which case we don't need to do anything
78
return self.app(scope, receive, send)