Description
In PyTorch before 2.7.0, when torch.compile is used, FractionalMaxPool2d has inconsistent results.
Affected products
linuxfoundation: pytorch
References4
- github.com/pytorch/pytorch/pull/144395 Issue TrackingPatch
- gist.github.com/shaoyuyoung/4bcefba4004f8271e64b5185c95a248a Third Party Advisory
- github.com/pytorch/pytorch/issues/141538 Issue Tracking
- github.com/pytorch/pytorch/issues/141538#issuecomment-2537424658 Issue Tracking
Metrics
- CVSS 3.1
-
5.3
MEDIUM
Score source: CNA
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:L/I:N/A:N - EPSS — exploit probability
- 0% percentile: 33 · as of 9 November 2026
Could this be exploited in your environment?
A patch closes the known hole. A penetration test shows what an attacker can still reach — with proof.