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

enable more test cases on xpu (#38572)

Browse Source 
* enable glm4 integration cases on XPU, set xpu expectation for blip2

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

* more

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

* fix style

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

* refine wording

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

* refine test case names

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

* run

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

* add gemma2 and chameleon

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

* fix review comments

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

---------

Signed-off-by: Matrix YAO <matrix.yao@intel.com>
Signed-off-by: YAO Matrix <matrix.yao@intel.com>
This commit is contained in:
Yao Matrix
2025-06-06 15:29:51 +08:00
committed by GitHub
parent 31023b6909
commit 89542fb81c
23 changed files with 150 additions and 72 deletions
Download Patch File Download Diff File Expand all files Collapse all files

8
tests/quantization/quark_integration/test_quark.py
View File

@@ -11,17 +11,18 @@
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
import gc
import unittest
from transformers import AutoConfig, AutoModelForCausalLM, AutoTokenizer, GenerationConfig, QuarkConfig
from transformers.testing_utils import (
cleanup,
is_torch_available,
require_accelerate,
require_quark,
require_torch_gpu,
require_torch_multi_gpu,
slow,
torch_device,
)
from transformers.utils.import_utils import is_quark_available
@@ -79,11 +80,10 @@ class QuarkTest(unittest.TestCase):
def tearDown(self):
r"""
TearDown function needs to be called at the end of each test to free the GPU memory and cache, also to
TearDown function needs to be called at the end of each test to free the accelerator memory and cache, also to
avoid unexpected behaviors. Please see: https://discuss.pytorch.org/t/how-can-we-release-gpu-memory-cache/14530/27
"""
gc.collect()
torch.cuda.empty_cache()
cleanup(torch_device, gc_collect=True)
def test_memory_footprint(self):
mem_quantized = self.quantized_model.get_memory_footprint()