Skip to content

[PyTorch] [torch.compile] Remove internal tensor state from Float8CurrentScalingQuantizer#2816

Draft
pggPL wants to merge 3 commits intoNVIDIA:mainfrom
pggPL:stateless_quantizers
Draft

[PyTorch] [torch.compile] Remove internal tensor state from Float8CurrentScalingQuantizer#2816
pggPL wants to merge 3 commits intoNVIDIA:mainfrom
pggPL:stateless_quantizers

Commits

Commits on Apr 16, 2026