taomiao opened a new issue, #15832:
URL: https://github.com/apache/tvm/issues/15832

   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 :smile_cat:
   
   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
   
   successfully run
   
   ### Actual behavior
   
   InternalError: Check failed: fshape_func.count(op) > 0 (0 vs. 0) : Internal 
error, cannot find ShapeFunc for sin
   
   ### Environment
   
   Operating System: ubuntu 20.04
   TVM version: 0.14.dev194+ga096b4cd0
   
   ### Steps to reproduce
   
   `import torch
   import tvm
   from tvm import relay
   
   class DSmodel(torch.nn.Module):
       def __init__(self):
           super().__init__()
   
       def forward(self, positions, freqs=2):
           gt0 = positions>0
           gt0_idx = gt0.nonzero(as_tuple=True)
           positions = positions[gt0_idx]
           freq_bands = (2 ** torch.arange(freqs).float()).to(positions.device) 
 # (F,)
           pts = (positions[..., None] * freq_bands).reshape(
               positions.shape[:-1] + (freqs * positions.shape[-1],))  # (..., 
DF)
           pts = torch.cat([torch.sin(pts), torch.cos(pts)], dim=-1)
           return pts
   
   model = DSmodel()
   pos = torch.rand([20, 3])
   pt_mod = torch.jit.trace(model, example_inputs=(pos,))
   
   mod, params = relay.frontend.from_pytorch(pt_mod, [("input0", (20, 3))])
   print(mod)
   
   target = tvm.target.Target(target="llvm")
   device = tvm.device(target.kind.name, 0)
   func = tvm.relay.create_executor(kind="vm", mod=mod, target=target, 
device=device).evaluate()
   func(pos.numpy())`
   
   ### Triage
   
   [* needs-triage](frontend:pytorch)
   


-- 
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.

To unsubscribe, e-mail: [email protected]

For queries about this service, please contact Infrastructure at:
[email protected]

Reply via email to