Enable memory saver for hybrid model (#11974)

2025-11-04 14:55:26 +08:00
parent f600866a44
commit 173e0f704f
3 changed files with 15 additions and 8 deletions
--- a/python/sglang/srt/model_executor/model_runner.py
+++ b/python/sglang/srt/model_executor/model_runner.py
@@ -1798,6 +1798,7 @@ class ModelRunner:
                    ),
                    enable_kvcache_transpose=False,
                    device=self.device,
+                    enable_memory_saver=self.server_args.enable_memory_saver,
                    mamba_pool=self.req_to_token_pool.mamba_pool,
                    use_mla=self.use_mla_backend,
                    **extra_args,