`torch.maximum` / `torch.clamp_min` gradients at tie point violate PyTorch's documented subgradient convention and are inconsistent with `F.relu`
May 20, 2026 · #184572
Python
Difficulty: Medium
Labels
module: autograd module: edge cases
Parent Repository
pytorch/pytorch
Python repository
100,083 27,851
Ready to work on this? Walk through the full fork-to-PR workflow so your first contribution goes smoothly.