diff --git a/megatron/core/pipeline_parallel/fine_grained_activation_offload.py b/megatron/core/pipeline_parallel/fine_grained_activation_offload.py
index 08e46a039e2..99f66d04de9 100644
--- a/megatron/core/pipeline_parallel/fine_grained_activation_offload.py
+++ b/megatron/core/pipeline_parallel/fine_grained_activation_offload.py
@@ -867,6 +867,8 @@ def tensor_need_offloading_checker(self, tensor):
         # Respect tensor's offload preference if specified
         if hasattr(tensor, "offloading_activation") and not tensor.offloading_activation:
             return False
+        if getattr(tensor, "_TE_do_not_offload", False):
+            return False
         return True
 
     def bulk_offload_group(self):