[Bug] linspace op gets wrong result

[taomiao]

Thanks for participating in the TVM community! We use https://discuss.tvm.ai for any general usage questions and discussions. The issue tracker is used for actionable items such as feature proposals discussion, roadmaps, and bug tracking. You are always welcomed to post on the forum first 😸

Issues that are inactive for a period of time may get closed. We adopt this policy so that we won't lose track of actionable issues that may fall at the bottom of the pile. Feel free to reopen a new one if you feel there is an additional problem that needs attention when an old one gets closed.

Expected behavior

work well

Actual behavior

test_forward.py:211: in verify_model
    assert_shapes_match(baseline_output, output)
_ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ 

tru = array([0.       , 0.8888889, 1.7777778, 2.6666667, 3.5555556, 4.4444447,
       5.3333335, 6.2222223, 7.111111 , 8.       ], dtype=float32)
est = array([0.       , 0.8888889, 1.7777778, 2.6666667, 3.5555556, 4.4444447,
       5.3333335, 6.2222223, 7.111111 , 8.       , 8.888889 ],
      dtype=float32)

    def assert_shapes_match(tru, est):
        """Verfiy whether the shapes are equal"""
        if tru.shape != est.shape:
            msg = "Output shapes {} and {} don't match"
>           raise AssertionError(msg.format(tru.shape, est.shape))
E           AssertionError: Output shapes (10,) and (11,) don't match

Environment

os: ubuntu
python: 3.9
pytorch: 2.0
tvm: main branch

Steps to reproduce

@tvm.testing.uses_gpu
def test_forward_linspace():
    """test_forward_linspace"""
    torch.set_grad_enabled(False)

    class Linspace9(Module):
        def forward(self, *args):
            return torch.linspace(0, 8, 10)

    verify_model(Linspace9().float().eval())

Triage

Please refer to the list of label tags here to find the relevant tags and add them below in a bullet format (example below).

• needs-triage
• frontend:pytorch