[CK_TILE] layernorm have more accurate residual (#1623)

* more accurate residual

* modify comment

* Fix literal case in README.md

---------

Co-authored-by: Po Yen Chen <PoYen.Chen@amd.com>
This commit is contained in:
carlushuang
2024-11-02 05:30:16 +00:00
committed by GitHub
parent 03c6448ba3
commit cb6c5d39dc
6 changed files with 97 additions and 63 deletions

View File

@@ -202,8 +202,9 @@ float layernorm2d_fwd_(const S& s, A a)
using Default2DEpilogueProblem = ck_tile::Default2DEpilogueProblem<ComputeDataType, YDataType, false, Traits_::kPadN, false>;
using Default2DEpilogue = ck_tile::Default2DEpilogue<Default2DEpilogueProblem>;
using DynamicQuantEpilogueProblem = ck_tile::DynamicQuantEpilogueProblem<ComputeDataType, YScaleDataType, YDataType, typename Traits_::Shape,
ck_tile::DynamicQuantEpilogueTraits<false, Traits_::kPadN, false, true/*max3*/>>;
static constexpr bool UseSmoothInputScale = Traits_::kFusedQuant == 1;
using DynamicQuantEpilogueProblem = ck_tile::DynamicQuantEpilogueProblem<ComputeDataType, XScaleDataType, YScaleDataType, YDataType, typename Traits_::Shape,
ck_tile::DynamicQuantEpilogueTraits<false, Traits_::kPadN, UseSmoothInputScale, false, true/*max3*/>>;
using DynamicQuantEpilogue = ck_tile::DynamicQuantEpilogue<DynamicQuantEpilogueProblem>;