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

switch to device agnostic device calling for test cases (#38247)

Browse Source 
* use device agnostic APIs in test cases

Signed-off-by: Matrix Yao <matrix.yao@intel.com>

* fix style

Signed-off-by: Matrix Yao <matrix.yao@intel.com>

* add one more

Signed-off-by: YAO Matrix <matrix.yao@intel.com>

* xpu now supports integer device id, aligning to CUDA behaviors

Signed-off-by: Matrix Yao <matrix.yao@intel.com>

* update to use device_properties

Signed-off-by: Matrix Yao <matrix.yao@intel.com>

* fix style

Signed-off-by: Matrix Yao <matrix.yao@intel.com>

* update comment

Signed-off-by: Matrix Yao <matrix.yao@intel.com>

* fix comments

Signed-off-by: Matrix Yao <matrix.yao@intel.com>

* fix style

Signed-off-by: Matrix Yao <matrix.yao@intel.com>

---------

Signed-off-by: Matrix Yao <matrix.yao@intel.com>
Signed-off-by: YAO Matrix <matrix.yao@intel.com>
Co-authored-by: ydshieh <ydshieh@users.noreply.github.com>
This commit is contained in:
Yao Matrix
2025-05-26 16:18:53 +08:00
committed by GitHub
parent cba279f46c
commit a5a0c7b888
39 changed files with 259 additions and 389 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
tests/quantization/compressed_tensors_integration/test_compressed_models.py
View File

@@ -3,7 +3,7 @@ import unittest
import warnings
from transformers import AutoModelForCausalLM, AutoTokenizer
from transformers.testing_utils import require_compressed_tensors, require_torch
from transformers.testing_utils import backend_empty_cache, require_compressed_tensors, require_torch, torch_device
from transformers.utils import is_torch_available
from transformers.utils.quantization_config import CompressedTensorsConfig
@@ -41,7 +41,7 @@ class StackCompressedModelTest(unittest.TestCase):
def tearDown(self):
gc.collect()
torch.cuda.empty_cache()
backend_empty_cache(torch_device)
gc.collect()
def test_compressed_uncompressed_model_shapes(self):
@@ -160,7 +160,7 @@ class RunCompressedTest(unittest.TestCase):
def tearDown(self):
gc.collect()
torch.cuda.empty_cache()
backend_empty_cache(torch_device)
gc.collect()
def test_default_run_compressed__True(self):

4
tests/quantization/compressed_tensors_integration/test_compressed_tensors.py
View File

@@ -2,7 +2,7 @@ import gc
import unittest
from transformers import AutoModelForCausalLM, AutoTokenizer, CompressedTensorsConfig
from transformers.testing_utils import require_compressed_tensors, require_torch
from transformers.testing_utils import backend_empty_cache, require_compressed_tensors, require_torch, torch_device
from transformers.utils import is_torch_available
@@ -22,7 +22,7 @@ class CompressedTensorsTest(unittest.TestCase):
def tearDown(self):
gc.collect()
torch.cuda.empty_cache()
backend_empty_cache(torch_device)
gc.collect()
def test_config_args(self):