[PyTorch] Make quantized-tensor repr safe#3146

Open

pggPL wants to merge 3 commits into

NVIDIA:mainfrom

pggPL:fp8_repr_fake_safe

Commits on Jun 25, 2026

Make quantized-tensor __repr__ fake-safe under torch.compile

pggPL
and
claude
committed
[pre-commit.ci] auto fixes from pre-commit.com hooks
pre-commit-ci[bot]
committed
Make quantized __repr__ fallback universal, drop FakeTensor-specific logic

pggPL
and
claude
committed