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

Change GPUS to GPUs (#36945)

Browse Source 
Signed-off-by: zhanluxianshen <zhanluxianshen@163.com>
Co-authored-by: Yih-Dar <2521628+ydshieh@users.noreply.github.com>
This commit is contained in:
湛露先生
2025-03-26 00:25:39 +08:00
committed by GitHub
parent 69632aadb7
commit ebd2029483
8 changed files with 9 additions and 9 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
tests/quantization/eetq_integration/test_eetq.py
View File

@@ -158,7 +158,7 @@ class EetqTest(unittest.TestCase):
def test_quantized_model_multi_gpu(self):
"""
Simple test that checks if the quantized model is working properly with multiple GPUs
set CUDA_VISIBLE_DEVICES=0,1 if you have more than 2 GPUS
set CUDA_VISIBLE_DEVICES=0,1 if you have more than 2 GPUs
"""
input_ids = self.tokenizer(self.input_text, return_tensors="pt").to(torch_device)
quantization_config = EetqConfig()

2
tests/quantization/fbgemm_fp8/test_fbgemm_fp8.py
View File

@@ -215,7 +215,7 @@ class FbgemmFp8Test(unittest.TestCase):
def test_quantized_model_multi_gpu(self):
"""
Simple test that checks if the quantized model is working properly with multiple GPUs
set CUDA_VISIBLE_DEVICES=0,1 if you have more than 2 GPUS
set CUDA_VISIBLE_DEVICES=0,1 if you have more than 2 GPUs
"""
input_ids = self.tokenizer(self.input_text, return_tensors="pt").to(torch_device)
quantization_config = FbgemmFp8Config()

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

@@ -193,7 +193,7 @@ class FP8QuantizerTest(unittest.TestCase):
def test_quantized_model_multi_gpu(self):
"""
Simple test that checks if the quantized model is working properly with multiple GPUs
set CUDA_VISIBLE_DEVICES=0,1 if you have more than 2 GPUS
set CUDA_VISIBLE_DEVICES=0,1 if you have more than 2 GPUs
"""
input_ids = self.tokenizer(self.input_text, return_tensors="pt").to(self.device_map)
quantization_config = FineGrainedFP8Config()

2
tests/quantization/higgs/test_higgs.py
View File

@@ -156,7 +156,7 @@ class HiggsTest(unittest.TestCase):
def test_quantized_model_multi_gpu(self):
"""
Simple test that checks if the quantized model is working properly with multiple GPUs
set CUDA_VISIBLE_DEVICES=0,1 if you have more than 2 GPUS
set CUDA_VISIBLE_DEVICES=0,1 if you have more than 2 GPUs
"""
input_ids = self.tokenizer(self.input_text, return_tensors="pt").to(torch_device)
quantization_config = HiggsConfig()

2
tests/quantization/torchao_integration/test_torchao.py
View File

@@ -255,7 +255,7 @@ class TorchAoGPUTest(TorchAoTest):
def test_int4wo_quant_multi_gpu(self):
"""
Simple test that checks if the quantized model int4 weight only is working properly with multiple GPUs
set CUDA_VISIBLE_DEVICES=0,1 if you have more than 2 GPUS
set CUDA_VISIBLE_DEVICES=0,1 if you have more than 2 GPUs
"""
quant_config = TorchAoConfig("int4_weight_only", **self.quant_scheme_kwargs)