AffineQuant.h 文件参考

#include "common/Export.h"
#include "common/Result.h"
#include <cstdint>
#include <span>
#include <vector>

浏览源代码.

类
struct	eve::tensor::affine::QuantizedActivation
	ONNX unsigned activation quantization; owns bytes and scalar parameters. 更多...
struct	eve::tensor::affine::ByteView
	Borrowed packed 8-bit values, valid for the duration of a synchronous call. 更多...
struct	eve::tensor::affine::ConvShape
	Explicit 1D/2D NCHW convolution geometry; missing 1D height is one. 更多...

命名空间
namespace	eve
	Build metadata (engine git commit, build time, third-party version).
namespace	eve::tensor
namespace	eve::tensor::affine

函数
Result< QuantizedActivation >	eve::tensor::affine::dynamicQuantize (std::span< const float > input)
	Quantize finite FP32 activations with ONNX DynamicQuantizeLinear semantics.
Result< std::vector< uint8_t > >	eve::tensor::affine::quantize (std::span< const float > input, float scale, int zeroPoint, bool signedValues)
	Affine quantization to int8/uint8 bytes, saturating and rounding ties to even.
Result< std::vector< float > >	eve::tensor::affine::dequantize (ByteView input, std::span< const float > scales, std::span< const int32_t > zeros, size_t inner=1)
	Affine dequantization using scalar or per-axis scale/zero point.
Result< std::vector< int32_t > >	eve::tensor::affine::matmul (ByteView a, ByteView b, size_t m, size_t k, size_t n, int aZero=0, int bZero=0, OnnxCompute *compute=nullptr)
	Integer row-major [M,K] x [K,N], subtracting scalar zero points.
Result< std::vector< int32_t > >	eve::tensor::affine::conv (ByteView x, ByteView w, const ConvShape &shape, int xZero, std::span< const int32_t > wZeros, OnnxCompute *compute=nullptr)
	Integer Conv, supporting groups, asymmetric padding and dilation.