From 3063398f7c89d9f25dc86e6b77bc0ecf40b1ce7c Mon Sep 17 00:00:00 2001
From: mgoin <michael@neuralmagic.com>
Date: Thu, 18 Jul 2024 17:57:36 -0400
Subject: [PATCH] Test

---
 tests/test_auto_fp8.py | 2 --
 1 file changed, 2 deletions(-)

diff --git a/tests/test_auto_fp8.py b/tests/test_auto_fp8.py
index dfe6e61..6717ae1 100644
--- a/tests/test_auto_fp8.py
+++ b/tests/test_auto_fp8.py
@@ -56,8 +56,6 @@ def preprocess(example):
     quantize_config = BaseQuantizeConfig(quant_method="fp8", activation_scheme="static")
 
     model = AutoFP8ForCausalLM.from_pretrained(model_id, quantize_config)
-    model.model.to("cpu")
-
     model.quantize(ds)
     model.save_quantized(quantized_model_dir)