diff --git a/python/sglang/srt/server_args.py b/python/sglang/srt/server_args.py index b2f47760c..4e0bfa79f 100644 --- a/python/sglang/srt/server_args.py +++ b/python/sglang/srt/server_args.py @@ -2389,6 +2389,7 @@ class ServerArgs: "(-1 means unlimited). When enabled, after each insert the shallowest eligible " "interior states beyond the cap are removed while their full KV remains. " "Tail, fork, and locked nodes are preserved. Must be -1 or a positive integer.", + NS("exec.mamba"), ] = -1 enable_mamba_cache_stochastic_rounding: A[ bool,