[RL] enable offloading hybrid linear attn model (#13336)

2025-11-16 17:12:52 +08:00
parent 4e19c1d541
commit 9509c4ccd3
2 changed files with 13 additions and 7 deletions
--- a/python/sglang/srt/model_executor/model_runner.py
+++ b/python/sglang/srt/model_executor/model_runner.py
@@ -1837,6 +1837,7 @@ class ModelRunner:
                    enable_kvcache_transpose=False,
                    device=self.device,
                    mamba_pool=self.req_to_token_pool.mamba_pool,
+                    enable_memory_saver=self.server_args.enable_memory_saver,
                    use_mla=self.use_mla_backend,
                    **extra_args,
                )