ExecuTorch execution crashed for narrow_copy.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,)', 'ArgType.Dim -1', 'ArgType.Index -1', 'ArgType.Length 0']
error:
[tensor_impl.h:133] In function size(), assert failed (dim < dim_ && dim >= 0): Dimension out of range (expected to be in range of [0, 0], but got -1
zsh: abort
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 meta_tuple for narrow_copy.default: a bool tensor of shape (1,), dimension -1, index -1, and length 0. Read the assertion at tensor_impl.h:133 and trace the narrow_copy.default execution path to determine why the invalid dimension reaches size(). Done means the case no longer aborts and its expected 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
- Active
- Clarity
- Needs clarification
- Newbie friendliness
- 42/100