[Core] Free CPU pinned memory on environment cleanup (vllm-project#10477

) Signed-off-by: Bowen Wang <[email protected]>
abmfy · Jan 24, 2025 · a8f69c2 · a8f69c2
1 parent 75b9e77
commit a8f69c2
Showing 1 changed file with 5 additions and 0 deletions.
diff --git a/vllm/distributed/parallel_state.py b/vllm/distributed/parallel_state.py
@@ -1183,6 +1183,11 @@ def cleanup_dist_env_and_memory(shutdown_ray: bool = False):
     from vllm.platforms import current_platform
     if not current_platform.is_cpu():
         torch.cuda.empty_cache()
+    try:
+        torch._C._host_emptyCache()
+    except AttributeError:
+        logger.warning(
+            "torch._C._host_emptyCache() only available in Pytorch >=2.5")
 
 
 def in_the_same_node_as(pg: Union[ProcessGroup, StatelessProcessGroup],