From de290658d6f4e7f9794258051f929f7ea424d792 Mon Sep 17 00:00:00 2001
From: Erin Ho <14718778+hchings@users.noreply.github.com>
Date: Fri, 24 Oct 2025 15:52:02 +0000
Subject: [PATCH] change to async

Signed-off-by: Erin Ho <14718778+hchings@users.noreply.github.com>
---
 tensorrt_llm/executor/ray_executor.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/tensorrt_llm/executor/ray_executor.py b/tensorrt_llm/executor/ray_executor.py
index 5d87fdc9bfc..e0c810d7565 100644
--- a/tensorrt_llm/executor/ray_executor.py
+++ b/tensorrt_llm/executor/ray_executor.py
@@ -208,7 +208,7 @@ def submit(self, request: GenerationRequest) -> GenerationResult:
             self.call_all_ray_workers("enqueue_request",
                                       leader_only=True,
                                       request=request,
-                                      async_call=False,
+                                      async_call=True,
                                       result_wait_queue=result.queue)
 
         return result