/*
 * 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/config.h"
#include "tensorrt_llm/common/cudaUtils.h"
#include <assert.h>
#include <cuda_fp16.h>
#include <cuda_runtime.h>

TRTLLM_NAMESPACE_BEGIN

namespace kernels
{
template <typename Tout, typename Tin, typename Idx>
void invokeLookUp(Tout* out, Idx const* input, Tin const* weight, int64_t const token_num, Idx const offset,
    Idx const size, Idx const n_embed, Tout const* perTokenScales, cudaStream_t stream = 0);

} // namespace kernels

TRTLLM_NAMESPACE_END