Skip to content

Refixing require_read_token #37427

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

Closed
wants to merge 2 commits into from
Closed

Refixing require_read_token #37427

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
94ea20a
refix
MekkCyber Apr 10, 2025
1a67ca1
Merge branch 'main' into fix_require_class
SunMarc Apr 11, 2025
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
6 changes: 1 addition & 5 deletions tests/quantization/quark_integration/test_quark.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -43,6 +43,7 @@ def test_commmon_args(self):
@slow
@require_quark
@require_torch_gpu
@require_read_token
class QuarkTest(unittest.TestCase):
reference_model_name = "meta-llama/Llama-3.1-8B-Instruct"
quantized_model_name = "amd/Llama-3.1-8B-Instruct-w-int8-a-int8-sym-test"
Expand Down Expand Up @@ -76,13 +77,11 @@ def setUpClass(cls):
device_map=cls.device_map,
)

@require_read_token
def test_memory_footprint(self):
mem_quantized = self.quantized_model.get_memory_footprint()

self.assertTrue(self.mem_fp16 / mem_quantized > self.EXPECTED_RELATIVE_DIFFERENCE)

@require_read_token
def test_device_and_dtype_assignment(self):
r"""
Test whether trying to cast (or assigning a device to) a model after quantization will throw an error.
Expand All @@ -96,7 +95,6 @@ def test_device_and_dtype_assignment(self):
# Tries with a `dtype``
self.quantized_model.to(torch.float16)

@require_read_token
def test_original_dtype(self):
r"""
A simple test to check if the model succesfully stores the original dtype
Expand All @@ -107,7 +105,6 @@ def test_original_dtype(self):

self.assertTrue(isinstance(self.quantized_model.model.layers[0].mlp.gate_proj, QParamsLinear))

@require_read_token
def check_inference_correctness(self, model):
r"""
Test the generation quality of the quantized model and see that we are matching the expected output.
Expand All @@ -131,7 +128,6 @@ def check_inference_correctness(self, model):
# Get the generation
self.assertIn(self.tokenizer.decode(output_sequences[0], skip_special_tokens=True), self.EXPECTED_OUTPUTS)

@require_read_token
def test_generate_quality(self):
"""
Simple test to check the quality of the model by comparing the generated tokens with the expected tokens
Expand Down