include_quantization_kernels.h

namespace ONNX_LIGHT_NAMESPACE

namespace onnx_backend_test

namespace kernel

class QuantizeLinear

#include <include_quantization_kernels.h>

Per-tensor linear quantization of a FLOAT input x to an 8-bit integer output. The output element type is taken from y_zero_point (UINT8 or INT8); if y_zero_point is omitted the output is UINT8 with a zero point of 0.

Public Functions

inline explicit QuantizeLinear(const KernelContext &ctx)

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

Omitted y_zero_point: output is UINT8 with zero point 0.

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

Tensor operator()(const Tensor &x, const Tensor &y_scale, const Tensor &y_zero_point) const

Explicit y_zero_point: its data_type drives the output element type.

void operator()(const Tensor &x, const Tensor &y_scale, const Tensor &y_zero_point, Tensor &output) const

Public Static Functions

static inline constexpr bool CanRunInPlace() noexcept

Output element type (UINT8/INT8) differs from the FLOAT input element type, so storage can never be shared with an input.

Private Members

KernelContext ctx_