diff --git a/python/sglang/srt/server_args.py b/python/sglang/srt/server_args.py index dbfd48efb..b5ae57817 100644 --- a/python/sglang/srt/server_args.py +++ b/python/sglang/srt/server_args.py @@ -371,7 +371,7 @@ class ServerArgs: # Mamba cache max_mamba_cache_size: Optional[int] = None mamba_ssm_dtype: str = "float32" - mamba_full_memory_ratio: float = 0.2 + mamba_full_memory_ratio: float = 0.9 # Hierarchical cache enable_hierarchical_cache: bool = False