From 9146fa443dca4768e428ae06fefe7c1ccc7e86b8 Mon Sep 17 00:00:00 2001
From: Daniel Han-Chen <danielhanchen@gmail.com>
Date: Fri, 2 Feb 2024 20:24:28 +1100
Subject: [PATCH] Update llama.py

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

diff --git a/unsloth/models/llama.py b/unsloth/models/llama.py
index 8024c915ff..7211015218 100644
--- a/unsloth/models/llama.py
+++ b/unsloth/models/llama.py
@@ -680,7 +680,6 @@ pass
 
 # https://github.com/huggingface/transformers/blob/main/src/transformers/models/llama/modeling_llama.py#L825
 @torch.compile
-@torch.inference_mode
 def LlamaModel_fast_forward_inference(
     self,
     input_ids,