Merge commit 'a69692ac' of...

Merge commit 'a69692ac' of https://github.com/NVIDIA/TransformerEngine

Merge commit 'a69692ac' of...
Merge commit 'a69692ac' of https://github.com/NVIDIA/TransformerEngine
2b05e121 · yuguo · 0fd441c2 · a69692ac · 2b05e121 · 2b05e121
Commit 2b05e121 authored Jun 17, 2025 by yuguo
20 changed files
--- a/transformer_engine/common/transpose/quantize_transpose_vector_blockwise.cu
+++ b/transformer_engine/common/transpose/quantize_transpose_vector_blockwise.cu
--- a/transformer_engine/common/transpose/transpose.cu
+++ b/transformer_engine/common/transpose/transpose.cu
--- a/transformer_engine/common/transpose/transpose_fusion.cu
+++ b/transformer_engine/common/transpose/transpose_fusion.cu
--- a/transformer_engine/common/util/cast.cu
+++ b/transformer_engine/common/util/cast.cu
--- a/transformer_engine/common/util/cast_gated_kernels.cuh
+++ b/transformer_engine/common/util/cast_gated_kernels.cuh
--- a/transformer_engine/common/util/cast_kernels.cuh
+++ b/transformer_engine/common/util/cast_kernels.cuh
--- a/transformer_engine/common/util/cuda_driver.cpp
+++ b/transformer_engine/common/util/cuda_driver.cpp
--- a/transformer_engine/common/util/cuda_driver.h
+++ b/transformer_engine/common/util/cuda_driver.h
--- a/transformer_engine/common/util/dequantize_kernels.cuh
+++ b/transformer_engine/common/util/dequantize_kernels.cuh
--- a/transformer_engine/common/util/multi_stream.cpp
+++ b/transformer_engine/common/util/multi_stream.cpp
--- a/transformer_engine/common/util/multi_stream.h
+++ b/transformer_engine/common/util/multi_stream.h
--- a/transformer_engine/common/util/padding.cu
+++ b/transformer_engine/common/util/padding.cu
--- a/transformer_engine/common/util/pybind_helper.h
+++ b/transformer_engine/common/util/pybind_helper.h
--- a/transformer_engine/common/utils.cuh
+++ b/transformer_engine/common/utils.cuh
--- a/transformer_engine/debug/features/api.py
+++ b/transformer_engine/debug/features/api.py
--- a/transformer_engine/debug/features/fake_quant.py
+++ b/transformer_engine/debug/features/fake_quant.py
--- a/transformer_engine/debug/features/log_fp8_tensor_stats.py
+++ b/transformer_engine/debug/features/log_fp8_tensor_stats.py
--- a/transformer_engine/debug/features/per_tensor_scaling.py
+++ b/transformer_engine/debug/features/per_tensor_scaling.py
--- a/transformer_engine/debug/features/utils/stats_computation.py
+++ b/transformer_engine/debug/features/utils/stats_computation.py
--- a/transformer_engine/debug/pytorch/debug_quantization.py
+++ b/transformer_engine/debug/pytorch/debug_quantization.py