[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
@@ -73,7 +73,7 @@ _COMMON_SERVER_ARGS = [
    "16384",
    "--max-running-requests",
    "256",
-    "--cuda-graph-max-bs",
+    "--cuda-graph-max-bs-decode",
    "256",
    "--attention-backend",
    "flashinfer",