Skip to content

[FIX] xpu unit test #2122

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 1 commit into from
Oct 27, 2025
Merged

[FIX] xpu unit test #2122

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
7 changes: 3 additions & 4 deletions tests/test_inference_result_xpu.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -25,16 +25,15 @@ class TestInferenceResultXPU(ModelTest):
(BACKEND.TORCH, DEVICE.XPU, False),
]
)
def testTritonXPU(self, backend, device, template):
def testTorchXPU(self, backend, device, template):
origin_model = GPTQModel.load(
self.NATIVE_MODEL_ID,
quantize_config=QuantizeConfig(),
quantize_config=QuantizeConfig(device=device),
backend=backend,
device=device,
)
tokenizer = self.load_tokenizer(self.NATIVE_MODEL_ID)
calibration_dataset = self.load_dataset(tokenizer, rows=128)
origin_model.quantize(calibration_dataset, backend=BACKEND.TRITON)
origin_model.quantize(calibration_dataset, backend=BACKEND.TORCH)

with tempfile.TemporaryDirectory() as tmpdir:
origin_model.save(tmpdir)
Expand Down
8 changes: 4 additions & 4 deletions tests/test_triton_xpu.py → tests/test_torch_xpu.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -18,25 +18,25 @@
from gptqmodel.models._const import DEVICE # noqa: E402


class TestTritonXPU(ModelTest):
class TestTorchXPU(ModelTest):
NATIVE_MODEL_ID = "/monster/data/model/Llama-3.2-1B-Instruct"

def test(self):
origin_model = GPTQModel.load(
self.NATIVE_MODEL_ID,
quantize_config=QuantizeConfig(),
backend=BACKEND.TRITON,
backend=BACKEND.TORCH,
device=DEVICE.XPU,
)
tokenizer = self.load_tokenizer(self.NATIVE_MODEL_ID)
calibration_dataset = self.load_dataset(tokenizer, self.DATASET_SIZE)
origin_model.quantize(calibration_dataset, backend=BACKEND.TRITON)
origin_model.quantize(calibration_dataset, backend=BACKEND.TORCH)
with tempfile.TemporaryDirectory() as tmpdir:
origin_model.save(tmpdir)

model = GPTQModel.load(
tmpdir,
backend=BACKEND.TRITON,
backend=BACKEND.TORCH,
device=DEVICE.XPU,
)
generate_str = tokenizer.decode(model.generate(**tokenizer("The capital of France is is", return_tensors="pt").to(model.device), max_new_tokens=2)[0])
Expand Down