wehub-resource-sync
103 lines
4.9 KiB
C++
103 lines
4.9 KiB
C++
// Copyright (c) 2023 PaddlePaddle Authors. All Rights Reserved.
|
|
//
|
|
// Licensed under the Apache License, Version 2.0 (the "License");
|
|
// you may not use this file except in compliance with the License.
|
|
// You may obtain a copy of the License at
|
|
//
|
|
// http://www.apache.org/licenses/LICENSE-2.0
|
|
//
|
|
// Unless required by applicable law or agreed to in writing, software
|
|
// distributed under the License is distributed on an "AS IS" BASIS,
|
|
// WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
|
// See the License for the specific language governing permissions and
|
|
// limitations under the License.
|
|
|
|
#pragma once
|
|
|
|
#include "paddle/phi/core/dense_tensor.h"
|
|
#include "paddle/phi/core/device_context.h"
|
|
#include "paddle/phi/core/kernel_registry.h"
|
|
|
|
namespace phi {
|
|
|
|
template <typename T, typename Context>
|
|
void QuantizeLinearKernel(const Context& dev_ctx,
|
|
const DenseTensor& x,
|
|
const optional<DenseTensor>& scale,
|
|
const DenseTensor& zero_point,
|
|
const optional<DenseTensor>& in_accum,
|
|
const optional<DenseTensor>& in_state,
|
|
int quant_axis,
|
|
int bit_length,
|
|
int qmin,
|
|
int qmax,
|
|
int round_type,
|
|
bool is_test,
|
|
bool only_observer,
|
|
DenseTensor* out,
|
|
DenseTensor* out_state,
|
|
DenseTensor* out_accum,
|
|
DenseTensor* out_scale);
|
|
|
|
template <typename T, typename Context>
|
|
void DeQuantizeLinearKernel(const Context& dev_ctx,
|
|
const DenseTensor& x,
|
|
const optional<DenseTensor>& scale,
|
|
const DenseTensor& zero_point,
|
|
const optional<DenseTensor>& in_accum,
|
|
const optional<DenseTensor>& in_state,
|
|
int quant_axis,
|
|
int bit_length,
|
|
int qmin,
|
|
int qmax,
|
|
int round_type,
|
|
bool is_test,
|
|
bool only_observer,
|
|
DenseTensor* out,
|
|
DenseTensor* out_state,
|
|
DenseTensor* out_accum,
|
|
DenseTensor* out_scale);
|
|
template <typename T, typename Context>
|
|
void DeQuantizeLinearDeprecatedKernel(const Context& dev_ctx,
|
|
const DenseTensor& x,
|
|
const DenseTensor& in_scale,
|
|
const DenseTensor& zero_point,
|
|
int quant_axis,
|
|
int bit_length,
|
|
int qmin,
|
|
int qmax,
|
|
int round_type,
|
|
bool only_observer,
|
|
DenseTensor* out);
|
|
template <typename T, typename Context>
|
|
void QuantizeLinearDeprecatedTrainKernel(const Context& dev_ctx,
|
|
const DenseTensor& x,
|
|
const DenseTensor& in_scale,
|
|
const DenseTensor& zero_point,
|
|
const optional<DenseTensor>& in_accum,
|
|
const optional<DenseTensor>& in_state,
|
|
int quant_axis,
|
|
int bit_length,
|
|
int qmin,
|
|
int qmax,
|
|
int round_type,
|
|
bool only_observer,
|
|
DenseTensor* out,
|
|
DenseTensor* out_state,
|
|
DenseTensor* out_accum,
|
|
DenseTensor* out_scale);
|
|
template <typename T, typename Context>
|
|
void QuantizeLinearDeprecatedInferKernel(const Context& dev_ctx,
|
|
const DenseTensor& x,
|
|
const DenseTensor& in_scale,
|
|
const DenseTensor& zero_point,
|
|
int quant_axis,
|
|
int bit_length,
|
|
int qmin,
|
|
int qmax,
|
|
int round_type,
|
|
bool only_observer,
|
|
DenseTensor* out);
|
|
|
|
} // namespace phi
|