include_text_kernels.h

namespace ONNX_LIGHT_NAMESPACE

namespace onnx_backend_test

namespace kernel

class StringConcat

#include <include_text_kernels.h>

Element-wise concatenation of two tensor(string) inputs with NumPy-style bidirectional broadcasting.

Public Functions

inline explicit StringConcat(const KernelContext &ctx)

Tensor operator()(const Tensor &x, const Tensor &y) const

void operator()(const Tensor &x, const Tensor &y, Tensor &output) const

Public Static Functions

static inline constexpr bool CanRunInPlace() noexcept

Output bytes depend on both inputs, so the output buffer cannot safely alias either input buffer.

Private Members

KernelContext ctx_