mirror of
https://github.com/NVIDIA/TensorRT-LLM.git
synced 2026-02-13 14:33:52 +08:00
31bb650298
Signed-off-by: Chenfei Zhang <chenfeiz@nvidia.com> Signed-off-by: Yilin Fan <206948969+nv-yilinf@users.noreply.github.com> Co-authored-by: Chenfei Zhang <chenfeiz@nvidia.com>
31 lines
1.1 KiB
C++
31 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 <cuda.h>
|
|
#include <cuda_bf16.h>
|
|
#include <cuda_fp8.h>
|
|
#include <cuda_runtime.h>
|
|
|
|
namespace tensorrt_llm::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 tensorrt_llm::kernels::llama4_min_latency::llama4_fp8_bf16_gemm
|