Commits


Adrian Lizarraga authored and GitHub committed 2b45410e52e
Fix Prefast warning in CUDA contrib op (#14074) ### Description Fixes Prefast C26814 ```shell onnxruntime::contrib::cuda::QAttention<onnxruntime::MLFloat16,signed char>::ComputeInternal onnxruntime/contrib_ops/cuda/quantization/attention_quantization.cc The const variable 'element_size' can be computed at compile-time. Consider using constexpr (con.5). ```