Log if cuda graph is used & extend cuda graph capture to cuda-graph-max-bs (#6201)

Co-authored-by: SangBin Cho <rkooo567@gmail.com>
2025-05-12 00:17:33 -07:00
parent 7d3a3d4510
commit fba8eccd7e
27 changed files with 293 additions and 121 deletions
--- a/python/sglang/srt/server_args.py
+++ b/python/sglang/srt/server_args.py
@@ -1086,7 +1086,7 @@ class ServerArgs:
            "--cuda-graph-max-bs",
            type=int,
            default=ServerArgs.cuda_graph_max_bs,
-            help="Set the maximum batch size for cuda graph.",
+            help="Set the maximum batch size for cuda graph. It will extend the cuda graph capture batch size to this value.",
        )
        parser.add_argument(
            "--cuda-graph-bs",