diff --git a/src/guidellm/backends/openai.py b/src/guidellm/backends/openai.py index 57e2d95a6..533dc17a3 100644 --- a/src/guidellm/backends/openai.py +++ b/src/guidellm/backends/openai.py @@ -134,6 +134,12 @@ async def process_startup(self): timeout=self.timeout, follow_redirects=self.follow_redirects, verify=self.verify, + # Allow unlimited connections with short keep-alive + limits=httpx.Limits( + max_connections=None, + max_keepalive_connections=None, + keepalive_expiry=0.5, + ), ) self._in_process = True