Enable MLA by default (#1447)

2024-09-17 19:42:48 +08:00
parent 90a26be31c
commit c6b6d2e71b
8 changed files with 16 additions and 18 deletions
--- a/python/sglang/srt/managers/schedule_batch.py
+++ b/python/sglang/srt/managers/schedule_batch.py
@@ -40,7 +40,7 @@ global_server_args_dict = {
    "attention_backend": ServerArgs.attention_backend,
    "sampling_backend": ServerArgs.sampling_backend,
    "triton_attention_reduce_in_fp32": ServerArgs.triton_attention_reduce_in_fp32,
-    "enable_mla": ServerArgs.enable_mla,
+    "disable_mla": ServerArgs.disable_mla,
    "torchao_config": ServerArgs.torchao_config,
 }