[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
@@ -211,7 +211,7 @@ def init_process_dst(
                str(base_gpu_id),
                "--tp-size",
                str(tp_size),
-                "--cuda-graph-max-bs",
+                "--cuda-graph-max-bs-decode",
                2,
                "--tokenizer-path",
                model_name,
@@ -222,7 +222,7 @@ def init_process_dst(
                str(base_gpu_id),
                "--tp-size",
                str(tp_size),
-                "--cuda-graph-max-bs",
+                "--cuda-graph-max-bs-decode",
                2,
                "--tokenizer-path",
                model_name,