Backend-agnostic implementation of quantized_layer_norm_per_tensor#13847

Merged

facebook-github-bot merged 2 commits intopytorch:mainfrom

DrJessop:export-D81459333

Sep 4, 2025

Commits on Sep 4, 2025

Update backend-agnostic quantize_per_tensor to use scale_inv to match the quantize_per_tensor_out implementation (#13846)

agrebenisan
authored and
facebook-github-bot
committed
Backend-agnostic implementation of quantized_layer_norm_per_tensor (#13847)

Andrew Grebenisan
authored and
facebook-github-bot
committed