SUMIN/HuggingFace_transformer
1
0
Fork 0
Code Issues Pull Requests Actions 7 Packages Projects Releases Wiki Activity

Add require_read_token to fp8 tests (#36189)

Browse Source 
fix
This commit is contained in:
Mohamed Mekkouri
2025-02-14 12:27:35 +01:00
committed by GitHub
parent 5f726f8b8e
commit cb586a3999
1 changed files with 2 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
tests/quantization/finegrained_fp8/test_fp8.py
View File

@@ -20,6 +20,7 @@ import unittest
from transformers import AutoConfig, AutoModelForCausalLM, AutoTokenizer, FineGrainedFP8Config, OPTForCausalLM from transformers import AutoConfig, AutoModelForCausalLM, AutoTokenizer, FineGrainedFP8Config, OPTForCausalLM
from transformers.testing_utils import ( from transformers.testing_utils import (
require_accelerate, require_accelerate,
require_read_token,
require_torch_gpu, require_torch_gpu,
require_torch_multi_gpu, require_torch_multi_gpu,
slow, slow,
@@ -59,6 +60,7 @@ class FineGrainedFP8ConfigTest(unittest.TestCase):
@slow @slow
@require_accelerate @require_accelerate
@require_read_token
@require_torch_gpu @require_torch_gpu
class FP8QuantizerTest(unittest.TestCase): class FP8QuantizerTest(unittest.TestCase):
model_name = "meta-llama/Llama-3.2-1B" model_name = "meta-llama/Llama-3.2-1B"