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

fix a bunch of XPU UT failures on stock PyTorch 2.7 and 2.8 (#39069)

Browse Source 
* fix a bunch of XPU UT failures on stock PyTorch 2.7 and 2.8

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

* qwen3

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

* quanto

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

* models

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

* fix style

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

* idefics2

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

---------

Signed-off-by: YAO Matrix <matrix.yao@intel.com>
This commit is contained in:
Yao Matrix
2025-06-27 20:01:53 +08:00
committed by GitHub
parent cb17103bd5
commit 0106a50a6b
9 changed files with 53 additions and 31 deletions
Download Patch File Download Diff File Expand all files Collapse all files

8
tests/quantization/quanto_integration/test_quanto.py
View File

@@ -223,7 +223,9 @@ class QuantoQuantizationTest(unittest.TestCase):
with tempfile.TemporaryDirectory() as tmpdirname:
with self.assertRaises(ValueError) as e:
self.quantized_model.save_pretrained(tmpdirname, safe_serialization=False)
self.assertIn("The model is quantized with quanto and is not serializable", str(e.exception))
self.assertIn(
"The model is quantized with QuantizationMethod.QUANTO and is not serializable", str(e.exception)
)
# TODO: replace by the following when it works
# quantized_model_from_saved = AutoModelForCausalLM.from_pretrained(
# tmpdirname, torch_dtype=torch.float32, device_map="cpu"
@@ -237,7 +239,9 @@ class QuantoQuantizationTest(unittest.TestCase):
with tempfile.TemporaryDirectory() as tmpdirname:
with self.assertRaises(ValueError) as e:
self.quantized_model.save_pretrained(tmpdirname)
self.assertIn("The model is quantized with quanto and is not serializable", str(e.exception))
self.assertIn(
"The model is quantized with QuantizationMethod.QUANTO and is not serializable", str(e.exception)
)
# quantized_model_from_saved = AutoModelForCausalLM.from_pretrained(
# tmpdirname, torch_dtype=torch.float32, device_map="cpu"
# )