From 8425f785ad58020ccda8b2d4d888f0a8be4af6c3 Mon Sep 17 00:00:00 2001
From: Varun Sundar Rabindranath <varunsundar08@gmail.com>
Date: Tue, 22 Jul 2025 12:05:45 +0530
Subject: [PATCH] [Misc] DeepEPHighThroughtput - Enable Inductor pass (#21311)

Signed-off-by: Varun Sundar Rabindranath <vsundarr@redhat.com>
Co-authored-by: Varun Sundar Rabindranath <vsundarr@redhat.com>
---
 vllm/platforms/cuda.py | 3 ---
 1 file changed, 3 deletions(-)

diff --git a/vllm/platforms/cuda.py b/vllm/platforms/cuda.py
index fdf1f46e603b4..cc2543538d0dc 100644
--- a/vllm/platforms/cuda.py
+++ b/vllm/platforms/cuda.py
@@ -182,9 +182,6 @@ class CudaPlatformBase(Platform):
             compilation_config.use_cudagraph = False
             if model_config is not None:
                 model_config.enforce_eager = True
-            # TODO (varun): Turning this ON gives incorrect results for the
-            # Deepseek-V2-lite model.
-            vllm_config.compilation_config.use_inductor = False
 
     @classmethod
     def get_current_memory_usage(cls,