diff --git a/python/sglang/srt/server_args.py b/python/sglang/srt/server_args.py index b94e35eb5..d93983ee0 100644 --- a/python/sglang/srt/server_args.py +++ b/python/sglang/srt/server_args.py @@ -8100,8 +8100,14 @@ class ServerArgs: if self.pp_size > 1: logger.warning("Optimistic prefill does not support pp_size > 1") self.optimistic_prefill_attempts = 0 - elif self.enable_hierarchical_cache: - logger.warning("Optimistic prefill does not support hierarchical cache") + elif self.enable_hierarchical_cache and ( + self.hicache_storage_backend is not None + or self.hicache_write_policy != "write_back" + ): + logger.warning( + "Optimistic prefill only supports L2 hierarchical cache " + "with write-back policy" + ) self.optimistic_prefill_attempts = 0 elif resolved_view(self).uses_mamba_radix_cache: logger.warning(