[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
@@ -44,7 +44,7 @@ class TestAnthropicVision(CustomTestCase):
            other_args=[
                "--trust-remote-code",
                "--enable-multimodal",
-                "--cuda-graph-max-bs=4",
+                "--cuda-graph-max-bs-decode=4",
            ],
        )
        cls.messages_url = cls.base_url + "/v1/messages"