@@ -56,7 +56,7 @@ args = [
"--max-model-len", "393216",
"--max-num-seqs", "8",
"--max-num-batched-tokens", "8192",
- "--max-cudagraph-capture-size", "56",
+# capture cap comes from the sizes list (max 8) — the 56 value would need 56 in the list
"--compilation-config", """
'{"cudagraph_mode":"FULL_AND_PIECEWISE","custom_ops":["all"],"cudagraph_capture_sizes":[1,2,3,4,5,6,7,8]}'""",
"--async-scheduling",