Merge commit '7a9a0825' of...

Merge commit '7a9a0825' of https://github.com/NVIDIA/TransformerEngine

Merge commit '7a9a0825' of...
Merge commit '7a9a0825' of https://github.com/NVIDIA/TransformerEngine
44740c6c · yuguo · 8113d9e0 · 7a9a0825 · 44740c6c · 44740c6c
Commit 44740c6c authored Jul 22, 2025 by yuguo
20 changed files
--- a/transformer_engine/common/transformer_engine.cpp
+++ b/transformer_engine/common/transformer_engine.cpp
@@ -46,6 +46,8 @@ std::string to_string(const DType type) {
      return "Float8E8M0";
    case DType::kFloat4E2M1:
      return "Float4E2M1";
+    case DType::kInt16:
+      return "Int16";
    case DType::kInt32:
      return "Int32";
    case DType::kInt64:

--- a/transformer_engine/common/util/cast_gated_kernels.cuh
+++ b/transformer_engine/common/util/cast_gated_kernels.cuh
--- a/transformer_engine/common/util/cuda_runtime.cpp
+++ b/transformer_engine/common/util/cuda_runtime.cpp
--- a/transformer_engine/common/util/cuda_runtime.h
+++ b/transformer_engine/common/util/cuda_runtime.h
--- a/transformer_engine/common/util/multi_stream.cpp
+++ b/transformer_engine/common/util/multi_stream.cpp
--- a/transformer_engine/common/util/padding.cu
+++ b/transformer_engine/common/util/padding.cu
--- a/transformer_engine/common/util/rtc.cpp
+++ b/transformer_engine/common/util/rtc.cpp
--- a/transformer_engine/debug/features/utils/stats_buffer.py
+++ b/transformer_engine/debug/features/utils/stats_buffer.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
--- a/transformer_engine/jax/cpp_extensions/activation.py
+++ b/transformer_engine/jax/cpp_extensions/activation.py
--- a/transformer_engine/jax/cpp_extensions/gemm.py
+++ b/transformer_engine/jax/cpp_extensions/gemm.py
--- a/transformer_engine/jax/cpp_extensions/misc.py
+++ b/transformer_engine/jax/cpp_extensions/misc.py
--- a/transformer_engine/jax/cpp_extensions/normalization.py
+++ b/transformer_engine/jax/cpp_extensions/normalization.py
--- a/transformer_engine/jax/cpp_extensions/quantization.py
+++ b/transformer_engine/jax/cpp_extensions/quantization.py
--- a/transformer_engine/jax/csrc/extensions.h
+++ b/transformer_engine/jax/csrc/extensions.h
--- a/transformer_engine/jax/csrc/extensions/ffi.cpp
+++ b/transformer_engine/jax/csrc/extensions/ffi.cpp
--- a/transformer_engine/jax/csrc/extensions/gemm.cpp
+++ b/transformer_engine/jax/csrc/extensions/gemm.cpp
--- a/transformer_engine/jax/csrc/extensions/misc.h
+++ b/transformer_engine/jax/csrc/extensions/misc.h
--- a/transformer_engine/jax/csrc/extensions/pybind.cpp
+++ b/transformer_engine/jax/csrc/extensions/pybind.cpp