From 016cf4ec1df2c067e3c6e97b51569d3fce573091 Mon Sep 17 00:00:00 2001
From: Nicolas Patry <patry.nicolas@protonmail.com>
Date: Wed, 25 Sep 2024 14:44:20 +0200
Subject: [PATCH] Ruff.

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

diff --git a/server/text_generation_server/models/custom_modeling/flash_llama_modeling.py b/server/text_generation_server/models/custom_modeling/flash_llama_modeling.py
index 634b09f7..8b439930 100644
--- a/server/text_generation_server/models/custom_modeling/flash_llama_modeling.py
+++ b/server/text_generation_server/models/custom_modeling/flash_llama_modeling.py
@@ -58,7 +58,7 @@ from text_generation_server.utils.weights import (
 from text_generation_server.layers.fp8 import HybridFP8UnquantLoader
 
 if SYSTEM != "ipex":
-    from vllm.model_executor.layers.fused_moe import fused_moe
+    pass
 
 if SYSTEM == "rocm":
     try: