Merge commit '04c730c0' of...

Merge commit '04c730c0' of https://github.com/NVIDIA/TransformerEngine

Merge commit '04c730c0' of...
Merge commit '04c730c0' of https://github.com/NVIDIA/TransformerEngine
ab3e5a92 · yuguo · a8d19fd9 · 04c730c0 · ab3e5a92 · ab3e5a92
Commit ab3e5a92 authored May 09, 2025 by yuguo
20 changed files
--- a/transformer_engine/common/gemm/cublaslt_gemm.cu
+++ b/transformer_engine/common/gemm/cublaslt_gemm.cu
--- a/transformer_engine/common/include/transformer_engine/cast.h
+++ b/transformer_engine/common/include/transformer_engine/cast.h
--- a/transformer_engine/common/include/transformer_engine/fused_rope.h
+++ b/transformer_engine/common/include/transformer_engine/fused_rope.h
--- a/transformer_engine/common/include/transformer_engine/normalization.h
+++ b/transformer_engine/common/include/transformer_engine/normalization.h
--- a/transformer_engine/common/include/transformer_engine/transformer_engine.h
+++ b/transformer_engine/common/include/transformer_engine/transformer_engine.h
--- a/transformer_engine/common/libtransformer_engine.version
+++ b/transformer_engine/common/libtransformer_engine.version
--- a/transformer_engine/common/normalization/common.cpp
+++ b/transformer_engine/common/normalization/common.cpp
--- a/transformer_engine/common/normalization/layernorm/ln_api.cpp
+++ b/transformer_engine/common/normalization/layernorm/ln_api.cpp
--- a/transformer_engine/common/normalization/rmsnorm/rmsnorm_api.cpp
+++ b/transformer_engine/common/normalization/rmsnorm/rmsnorm_api.cpp
--- a/transformer_engine/common/nvshmem_api/CMakeLists.txt
+++ b/transformer_engine/common/nvshmem_api/CMakeLists.txt
--- a/transformer_engine/common/nvshmem_api/nvshmem_waitkernel.cu
+++ b/transformer_engine/common/nvshmem_api/nvshmem_waitkernel.cu
--- a/transformer_engine/common/nvshmem_api/nvshmem_waitkernel.h
+++ b/transformer_engine/common/nvshmem_api/nvshmem_waitkernel.h
--- a/transformer_engine/common/permutation/permutation.cu
+++ b/transformer_engine/common/permutation/permutation.cu
--- a/transformer_engine/common/recipe/__init__.py
+++ b/transformer_engine/common/recipe/__init__.py
--- a/transformer_engine/common/recipe/current_scaling.cu
+++ b/transformer_engine/common/recipe/current_scaling.cu
--- a/transformer_engine/common/recipe/recipe_common.cuh
+++ b/transformer_engine/common/recipe/recipe_common.cuh
--- a/transformer_engine/common/transformer_engine.cpp
+++ b/transformer_engine/common/transformer_engine.cpp
--- a/transformer_engine/common/transpose/cast_transpose.h
+++ b/transformer_engine/common/transpose/cast_transpose.h
--- a/transformer_engine/common/transpose/quantize_transpose_square_blockwise.cu
+++ b/transformer_engine/common/transpose/quantize_transpose_square_blockwise.cu
--- a/transformer_engine/common/transpose/quantize_transpose_vector_blockwise.cu
+++ b/transformer_engine/common/transpose/quantize_transpose_vector_blockwise.cu