pytorch / pytorch/executorch

yolo26 does not export on the portable backend

Open
#21,621 0 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

bug module: examples module: kernels
Dominant language
Python
Stars
5k
Forks
1.2k
Avg merge
2d 10h
Merged PRs (30d)
581

Description

yolo26 does not export successfully on the portable backend. The gathered test-models-linux (yolo26, portable) job has been red since the model was added and has never had a green run.

Failure signature:

Expected tensor to have default or channels last dim order, but got dim_order(0)=0 (1)=2 (2)=1 (3)=3
kernel_ops_util.cpp:384 -> op_convolution.cpp:377
KernelCall failed at instruction 0:0 in aten::convolution.out: 0x12

An AOT pass emits a 4D dim order of (0, 2, 1, 3), which the portable convolution kernel rejects.

Because the job never passed, it produces no signal and only adds a permanently red entry to every periodic run, so #21618 skips yolo26 in .ci/scripts/gather_test_models.py.

To close this issue: make yolo26 export cleanly on the portable backend, then remove the skip in model_should_run_on_target_os so the job is gathered again.

yolo26 was contributed as an OpenVINO / XNNPACK example in #18583, and those paths, along with RISC-V, are unaffected and still tested.

cc @mergennachin @iseeyuan @lucylq @helunwencser @tarun292 @kimishpatel @jackzhxng @larryliu0820 @manuelcandales @JakeStevens

Contributor guide

Open the contributing guide

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Research direction

Start by reproducing the failing test-models-linux (yolo26, portable) job and inspect the reported AOT dim-order failure. Read .ci/scripts/gather_test_models.py and the model_should_run_on_target_os skip added by #21618. Done means yolo26 exports cleanly on portable and the skip is removed so the job is gathered again.

Written by the indexing model from the issue text.

Assessment

Tech stack
python
Domain
embedded-iot, machine-learning
Issue type
Bug
Difficulty
4/5
Estimated time
3-5 days
Activity status
Quiet
Clarity
Mostly clear
Newbie friendliness
58/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.