Skip to content

Fix 2 CPU failures in cpu-torch-latest #8629

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
hwchen2017 merged 2 commits into from
Sep 23, 2026
+3 −2
Merged

Fix 2 CPU failures in cpu-torch-latest #8629

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
33322f2
Fix AttributeError for pytest mismatch
jinyouzhi Sep 22, 2026
0b1d39b
Skip half int8 quantization on CPU
jinyouzhi Sep 23, 2026
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
4 changes: 2 additions & 2 deletions tests/unit/checkpoint/test_convert_checkpoint.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -160,6 +160,6 @@ def test_convert_zero_checkpoint_to_fp32_state_dict(self, tmpdir):
assert tensor.dtype == torch.bfloat16
torch.testing.assert_close(tensor.float(), state_dict[name], rtol=5e-3, atol=5e-3)

fp32_size = (fp32_save_dir / 'pytorch_model.bin').stat().st_size
bf16_size = (bf16_save_dir / 'pytorch_model.bin').stat().st_size
fp32_size = (fp32_save_dir / 'pytorch_model.bin').stat().size
bf16_size = (bf16_save_dir / 'pytorch_model.bin').stat().size
assert bf16_size < fp32_size * 0.6
1 change: 1 addition & 0 deletions tests/unit/inference/quantization/test_intX_quantization.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -378,6 +378,7 @@ def test_float_int8_quantization(self):
reset_random()
quantization_test_helper(torch.float32, 8)

@pytest.mark.skipif(device == 'cpu', reason='CPU does support FP16 GEMM')
def test_half_int8_quantization(self):
reset_random()
quantization_test_helper(torch.float16, 8)
Expand Down
Loading