Higher priority for user input of max_prefill_tokens & format (#540)

2024-06-12 21:48:40 -07:00
parent 1374334d38
commit fb9296f0ed
50 changed files with 817 additions and 569 deletions
--- a/python/sglang/launch_server.py
+++ b/python/sglang/launch_server.py
@@ -10,4 +10,4 @@ if __name__ == "__main__":
    args = parser.parse_args()
    server_args = ServerArgs.from_cli_args(args)

-    launch_server(server_args, None)
+    launch_server(server_args, None)