From 0d5c76a37f65f4895213f2ecbde1ac9b19cfaeb4 Mon Sep 17 00:00:00 2001
From: Daniel Han <danielhanchen@gmail.com>
Date: Fri, 14 Mar 2025 00:16:24 -0700
Subject: [PATCH] Update llama.py

---
 unsloth/models/llama.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/unsloth/models/llama.py b/unsloth/models/llama.py
index 0bb8c4a771..38801d23db 100644
--- a/unsloth/models/llama.py
+++ b/unsloth/models/llama.py
@@ -2659,7 +2659,7 @@ class FastLlamaModel:
         pass
 
         # Patch for fast inference
-        vllm_engine = getattr(model, "vllm_engine")
+        vllm_engine = getattr(model, "vllm_engine", None)
         if vllm_engine is not None:
             model.vllm_engine = vllm_engine
             model.fast_generate = vllm_fast_generate