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

fix xpu tests (#36656)

Browse Source 
* fix awq xpu tests

Signed-off-by: jiqing-feng <jiqing.feng@intel.com>

* update

Signed-off-by: jiqing-feng <jiqing.feng@intel.com>

* fix llava next video bnb tests

Signed-off-by: jiqing-feng <jiqing.feng@intel.com>

---------

Signed-off-by: jiqing-feng <jiqing.feng@intel.com>
Co-authored-by: Marc Sun <57196510+SunMarc@users.noreply.github.com>
This commit is contained in:
jiqing-feng
2025-03-17 22:57:49 +08:00
committed by GitHub
parent da7d64f4ff
commit 27361bd218
3 changed files with 19 additions and 11 deletions
Download Patch File Download Diff File Expand all files Collapse all files

17
tests/quantization/autoawq/test_awq.py
View File

@@ -59,16 +59,21 @@ class AwqConfigTest(unittest.TestCase):
with self.assertRaises(ValueError):
AwqConfig(bits=4, backend="unexisting-backend")
compute_capability = torch.cuda.get_device_capability()
major, minor = compute_capability
# Only cuda device can run this function
support_llm_awq = False
if torch.cuda.is_available():
compute_capability = torch.cuda.get_device_capability()
major, minor = compute_capability
if major >= 8:
support_llm_awq = True
if major < 8:
if support_llm_awq:
# LLMAWQ should work on an A100
AwqConfig(bits=4, backend="llm-awq")
else:
# LLMAWQ does not work on a T4
with self.assertRaises(ValueError):
AwqConfig(bits=4, backend="llm-awq")
else:
# LLMAWQ should work on an A100
AwqConfig(bits=4, backend="llm-awq")
def test_to_dict(self):
"""