Merge nv_main(2.10) to main

Signed-off-by: wenjh <wenjh@sugon.com>

Merge nv_main(2.10) to main
Signed-off-by: wenjh <wenjh@sugon.com>
c1a1c04e · wenjh · e698a0a7 · 66aed3ae · c1a1c04e · c1a1c04e
Commit c1a1c04e authored Dec 27, 2025 by wenjh
20 changed files
--- a/transformer_engine/jax/quantize/dequantizer.py
+++ b/transformer_engine/jax/quantize/dequantizer.py
--- a/transformer_engine/jax/quantize/hadamard.py
+++ b/transformer_engine/jax/quantize/hadamard.py
--- a/transformer_engine/jax/quantize/helper.py
+++ b/transformer_engine/jax/quantize/helper.py
--- a/transformer_engine/jax/quantize/metadata.py
+++ b/transformer_engine/jax/quantize/metadata.py
--- a/transformer_engine/jax/quantize/misc.py
+++ b/transformer_engine/jax/quantize/misc.py
--- a/transformer_engine/jax/quantize/quantizer.py
+++ b/transformer_engine/jax/quantize/quantizer.py
--- a/transformer_engine/jax/quantize/scaling_modes.py
+++ b/transformer_engine/jax/quantize/scaling_modes.py
--- a/transformer_engine/jax/quantize/tensor.py
+++ b/transformer_engine/jax/quantize/tensor.py
--- a/transformer_engine/jax/setup.py
+++ b/transformer_engine/jax/setup.py
--- a/transformer_engine/jax/sharding.py
+++ b/transformer_engine/jax/sharding.py
--- a/transformer_engine/pytorch/__init__.py
+++ b/transformer_engine/pytorch/__init__.py
--- a/transformer_engine/pytorch/attention/dot_product_attention/backends.py
+++ b/transformer_engine/pytorch/attention/dot_product_attention/backends.py
--- a/transformer_engine/pytorch/attention/dot_product_attention/context_parallel.py
+++ b/transformer_engine/pytorch/attention/dot_product_attention/context_parallel.py
--- a/transformer_engine/pytorch/attention/dot_product_attention/dot_product_attention.py
+++ b/transformer_engine/pytorch/attention/dot_product_attention/dot_product_attention.py
--- a/transformer_engine/pytorch/attention/dot_product_attention/utils.py
+++ b/transformer_engine/pytorch/attention/dot_product_attention/utils.py
--- a/transformer_engine/pytorch/attention/multi_head_attention.py
+++ b/transformer_engine/pytorch/attention/multi_head_attention.py
--- a/transformer_engine/pytorch/attention/rope.py
+++ b/transformer_engine/pytorch/attention/rope.py
--- a/transformer_engine/pytorch/cpp_extensions/fused_attn.py
+++ b/transformer_engine/pytorch/cpp_extensions/fused_attn.py
--- a/transformer_engine/pytorch/cpp_extensions/gemm.py
+++ b/transformer_engine/pytorch/cpp_extensions/gemm.py
--- a/transformer_engine/pytorch/cpu_offload.py
+++ b/transformer_engine/pytorch/cpu_offload.py