From cb586a39994ae4ca9dfca2993b8e298897fd4e5b Mon Sep 17 00:00:00 2001
From: Mohamed Mekkouri <93391238+MekkCyber@users.noreply.github.com>
Date: Fri, 14 Feb 2025 12:27:35 +0100
Subject: [PATCH] Add require_read_token to fp8 tests (#36189)

fix
---
 tests/quantization/finegrained_fp8/test_fp8.py | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/tests/quantization/finegrained_fp8/test_fp8.py b/tests/quantization/finegrained_fp8/test_fp8.py
index f86898b40b..f572567ed1 100644
--- a/tests/quantization/finegrained_fp8/test_fp8.py
+++ b/tests/quantization/finegrained_fp8/test_fp8.py
@@ -20,6 +20,7 @@ import unittest
 from transformers import AutoConfig, AutoModelForCausalLM, AutoTokenizer, FineGrainedFP8Config, OPTForCausalLM
 from transformers.testing_utils import (
     require_accelerate,
+    require_read_token,
     require_torch_gpu,
     require_torch_multi_gpu,
     slow,
@@ -59,6 +60,7 @@ class FineGrainedFP8ConfigTest(unittest.TestCase):
 
 @slow
 @require_accelerate
+@require_read_token
 @require_torch_gpu
 class FP8QuantizerTest(unittest.TestCase):
     model_name = "meta-llama/Llama-3.2-1B"