mirror of
https://github.com/PaddlePaddle/FastDeploy.git
synced 2025-10-16 05:30:58 +08:00
9205c88da1
Some checks failed
CE Compile Job / ce_job_pre_check (push) Has been cancelled
CE Compile Job / print_ce_job_pre_check_outputs (push) Has been cancelled
CE Compile Job / FD-Clone-Linux (push) Has been cancelled
CE Compile Job / Show Code Archive Output (push) Has been cancelled
CE Compile Job / BUILD_SM8090 (push) Has been cancelled
CE Compile Job / BUILD_SM8689 (push) Has been cancelled
CE Compile Job / CE_UPLOAD (push) Has been cancelled
Deploy GitHub Pages / deploy (push) Has been cancelled
48 lines
1.6 KiB
C++
48 lines
1.6 KiB
C++
// Copyright (c) 2022 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 <string>
|
|
#include <vector>
|
|
#include "helper.h"
|
|
|
|
|
|
|
|
std::vector<paddle::Tensor> W4AFp8Gemm(
|
|
const paddle::Tensor& input,
|
|
const paddle::Tensor& weight,
|
|
const paddle::Tensor& tokens, // If tokenpadding=0, this tensor represents the prefix sum of tensors, otherwise it represents the number of tokens in each group
|
|
const paddle::Tensor& input_row_sum,
|
|
const paddle::Tensor& weight_scale,
|
|
const int64_t token_padding_size,
|
|
const int64_t max_tokens,
|
|
const bool is_bfloat16);
|
|
|
|
template <typename InputType, typename OutputType>
|
|
void DisPatchW4AFp8GemmWrapper(
|
|
const InputType* input,
|
|
const InputType* weight,
|
|
const int64_t * tokens,
|
|
const float * input_row_sum,
|
|
const float * row_scale,
|
|
const float * weight_scale,
|
|
OutputType * out,
|
|
const int64_t token_padding_size,
|
|
const int64_t max_tokens,
|
|
const int num_experts,
|
|
const int64_t M,
|
|
const int64_t K,
|
|
cudaStream_t stream);
|