diff --git a/tensorrt_llm/commands/serve.py b/tensorrt_llm/commands/serve.py
index 6689bac1e27c..eba2403797fe 100644
--- a/tensorrt_llm/commands/serve.py
+++ b/tensorrt_llm/commands/serve.py
@@ -182,6 +182,10 @@ def launch_server(host: str,
                           server_role=server_role,
                           metadata_server_cfg=metadata_server_cfg)
 
+    # Optionally disable GC (default: not disabled)
+    if os.getenv("TRTLLM_SERVER_DISABLE_GC", "0") == "1":
+        gc.disable()
+
     asyncio.run(server(host, port))
 
 
@@ -518,7 +522,7 @@ def disaggregated(config_file: Optional[str],
     #   increment, and observed that `count0` (obtained by `gc.get_count()`)
     #   increases by fewer than 1,000 after every 200,000 requests, while the
     #   maximum value of `count0` exceeded 3,000,000 during the test.
-    if int(os.getenv("TRTLLM_DISAGG_SERVER_DISABLE_GC", "1")):
+    if os.getenv("TRTLLM_DISAGG_SERVER_DISABLE_GC", "1") == "1":
         gc.disable()
 
     asyncio.run(server(disagg_cfg.hostname, disagg_cfg.port))
diff --git a/tensorrt_llm/executor/worker.py b/tensorrt_llm/executor/worker.py
index f653587d20f7..148cdcf038c4 100644
--- a/tensorrt_llm/executor/worker.py
+++ b/tensorrt_llm/executor/worker.py
@@ -1,3 +1,4 @@
+import gc
 import json
 import os
 import time
@@ -413,6 +414,10 @@ def notify_proxy_threads_to_quit():
                 logger.error("Failed to deliver error message to proxy")
         return
 
+    # Optionally disable GC (default: not disabled)
+    if os.getenv("TRTLLM_WORKER_DISABLE_GC", "0") == "1":
+        gc.disable()
+
     with worker:
         try:
             worker.block_subordinates()