TensorRT-LLMs/cpp/tensorrt_llm/kernels/llama4MinLatencyKernels/llama4Fp8Bf16Gemm.h
Yihan Wang 9df4dad3b6
[None][fix] Introduce inline namespace to avoid symbol collision (#9541)
Signed-off-by: Yihan Wang <yihwang@nvidia.com>
2025-12-12 23:32:15 +08:00

36 lines
1.1 KiB
C++

/*
* Copyright (c) 2025-2025, 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 <cuda.h>
#include <cuda_bf16.h>
#include <cuda_fp8.h>
#include <cuda_runtime.h>
TRTLLM_NAMESPACE_BEGIN
namespace kernels::llama4_min_latency::llama4_fp8_bf16_gemm
{
void llama4_fp8_bf16_gemm_op(void const* A, void const* B, void* C, void const* scaling_factor, void const* pos_ids,
bool pos_ids_int64, int num_tokens, int hidden_in, int hidden_out, cudaStream_t stream);
} // namespace kernels::llama4_min_latency::llama4_fp8_bf16_gemm
TRTLLM_NAMESPACE_END