[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
@@ -61,7 +61,7 @@ class TestDSV4FlashPDDisaggNIXL(PDDisaggregationServerBase):
            "deepep",
            "--deepep-config",
            DEEPEP_CONFIG,
-            "--cuda-graph-max-bs",
+            "--cuda-graph-max-bs-decode",
            "128",
            "--max-running-requests",
            "256",
@@ -103,7 +103,7 @@ class TestDSV4FlashPDDisaggNIXL(PDDisaggregationServerBase):
            "deepep",
            "--deepep-config",
            DEEPEP_CONFIG,
-            "--cuda-graph-max-bs",
+            "--cuda-graph-max-bs-decode",
            "128",
            "--max-running-requests",
            "256",