mirror of
https://github.com/NVIDIA/TensorRT-LLM.git
synced 2026-01-14 06:27:45 +08:00
bca9a33b02
* Update TensorRT-LLM --------- Co-authored-by: Timur Abishev <abishev.timur@gmail.com> Co-authored-by: MahmoudAshraf97 <hassouna97.ma@gmail.com> Co-authored-by: Saeyoon Oh <saeyoon.oh@furiosa.ai> Co-authored-by: hattizai <hattizai@gmail.com>
37 lines
1.2 KiB
C++
37 lines
1.2 KiB
C++
/*
|
|
* Copyright (c) 2019-2023, NVIDIA CORPORATION. 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 "tensorrt_llm/common/quantization.h"
|
|
#include <cuda_fp16.h>
|
|
#include <cuda_runtime.h>
|
|
|
|
namespace tensorrt_llm
|
|
{
|
|
namespace kernels
|
|
{
|
|
|
|
template <typename T>
|
|
void invokeQuantization(
|
|
int8_t* dst, T const* src, const int64_t size, float const* scalePtr, cudaStream_t stream = 0, int maxGirdSize = 0);
|
|
|
|
template <typename T, typename QuantT>
|
|
void invokePerTokenQuantization(QuantT* dst, T const* src, const int64_t numRows, const int64_t numCols,
|
|
float const* clampPtr, float* scalePtr, tensorrt_llm::common::QuantMode quantMode, cudaStream_t stream = 0);
|
|
|
|
} // namespace kernels
|
|
} // namespace tensorrt_llm
|