diff --git a/vllm/v1/worker/gpu_model_runner.py b/vllm/v1/worker/gpu_model_runner.py
index 2c40853742ac9..db676e2819bf4 100644
--- a/vllm/v1/worker/gpu_model_runner.py
+++ b/vllm/v1/worker/gpu_model_runner.py
@@ -404,14 +404,17 @@ def execute_model(
 
     def load_model(self) -> None:
         if self.use_cuda_graph:
-            # FIXME(woosuk): Currently, we do not use inductor to reduce the
-            # compilation time and any potential issues with the inductor.
-            os.environ["VLLM_CUSTOM_OPS"] = "all"
+            # NOTE(woosuk): Currently, we use inductor because the piecewise
+            # CUDA graphs do not work properly with the custom CUDA kernels.
+            # FIXME(woosuk): Disable inductor to reduce the compilation time
+            # and avoid any potential issues with the inductor.
+            os.environ["VLLM_CUSTOM_OPS"] = "none"
             set_compilation_config(
                 CompilationConfig(
                     use_cudagraph=True,
                     non_cudagraph_ops=["vllm.unified_v1_flash_attention"],
-                    use_inductor=False,
+                    use_inductor=True,
+                    enable_fusion=False,
                 ))
 
         logger.info("Starting to load model %s...", self.model_config.model)