[misc] Use --cuda-graph-max-bs-decode in tests, examples, and docs (#29591)

2026-06-28 18:38:28 -07:00
parent 3217410cf6
commit 909123ddb8
140 changed files with 304 additions and 290 deletions
@@ -26,7 +26,7 @@ class TestVertexEndpoint(CustomTestCase):
            cls.model,
            cls.base_url,
            timeout=DEFAULT_TIMEOUT_FOR_SERVER_LAUNCH,
-            other_args=["--cuda-graph-max-bs", 2],
+            other_args=["--cuda-graph-max-bs-decode", 2],
        )

    @classmethod