[misc] Use --cuda-graph-max-bs-decode in tests, examples, and docs (#29591)
This commit is contained in:
@@ -69,7 +69,7 @@ common_args = [
|
||||
"12288",
|
||||
"--attention-backend",
|
||||
"aiter",
|
||||
"--cuda-graph-max-bs",
|
||||
"--cuda-graph-max-bs-decode",
|
||||
"32",
|
||||
]
|
||||
|
||||
|
||||
Reference in New Issue
Block a user