From a07c4c59392aeffd619ac0a6a1c10fc364cf6840 Mon Sep 17 00:00:00 2001
From: Ofir Zafrir <ofir.zafrir@intel.com>
Date: Thu, 26 Feb 2026 09:15:16 +0200
Subject: [PATCH] [BugFix][XPU] Fix speculative decoding on Intel XPU due to
 bug with `IGC_ForceOCLSIMDWidth=16` (#35298)

Signed-off-by: Ofir Zafrir <ofir.zafrir@intel.com>
Co-authored-by: Kunshang Ji <kunshang.ji@intel.com>
---
 vllm/platforms/xpu.py | 3 ---
 1 file changed, 3 deletions(-)

diff --git a/vllm/platforms/xpu.py b/vllm/platforms/xpu.py
index 454d2301e..c97c3297e 100644
--- a/vllm/platforms/xpu.py
+++ b/vllm/platforms/xpu.py
@@ -201,9 +201,6 @@ class XPUPlatform(Platform):
 
         if vllm_config.lora_config is not None:
             compilation_config.mode = CompilationMode.NONE
-        # decrease triton kernel compilation scratch space for speculative decoding
-        if vllm_config.speculative_config is not None:
-            os.environ["IGC_ForceOCLSIMDWidth"] = "16"  # noqa: SIM112
         # check and update parallel config
         parallel_config = vllm_config.parallel_config
         # Only override worker_cls if it's still the default "auto"