ExecuTorch execution failed for masked_select.default
Open
Nobody has claimed this yet.
module: kernels
triaged
- Dominant language
- Python
- Stars
- 5k
- Forks
- 1.2k
- Avg merge
- 2d 10h
- Merged PRs (30d)
- 581
Description
🕵️♂️ Detected with FACTO
🐛 Describe the bug
FACTO Generated meta_tuple:
['ArgType.Tensor torch.bool (1, 6, 8)', 'ArgType.Tensor torch.bool (2, 2, 2, 8, 1, 8)']
error:
[tensor_impl.cpp:127] Attempted to resize a bounded tensor with a maximum capacity of 392 elements to 4368 elements.
[op_masked_select.cpp:74] Check failed (resize_tensor(out, {out_numel}) == Error::Ok):
[method.cpp:1353] KernelCall failed at instruction 0:0 in operator aten::masked_select.out: 0x12
[method.cpp:1359] arg 0 with type id 1
[method.cpp:1359] arg 1 with type id 1
[method.cpp:1359] arg 2 with type id 1
[method.cpp:1359] arg 3 with type id 1
Versions
nightly
cc @larryliu0820
Contributor guide
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
Research direction
Start by reproducing the FACTO-generated masked_select.default case with the two reported tensor shapes, then inspect op_masked_select.cpp and tensor_impl.cpp around the reported checks. Trace why the bounded output capacity is insufficient; done means this input no longer fails the resize check and the relevant behavior is covered by a regression test.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- pytorch
- Domain
- embedded-iot, machine-learning
- Issue type
- Bug
- Difficulty
- 4/5
- Estimated time
- 3-5 days
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 30/100