mirror of
https://github.com/NVIDIA/TensorRT-LLM.git
synced 2026-01-14 06:27:45 +08:00
0ab9d17a59
* Update TensorRT-LLM --------- Co-authored-by: Shixiaowei02 <39303645+Shixiaowei02@users.noreply.github.com>
42 lines
1.0 KiB
Plaintext
42 lines
1.0 KiB
Plaintext
/*
|
|
* Copyright (c) 2020-2023, 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.
|
|
*/
|
|
|
|
#include "decoderMaskedMultiheadAttentionLaunch.h"
|
|
|
|
namespace tensorrt_llm
|
|
{
|
|
namespace kernels
|
|
{
|
|
|
|
namespace
|
|
{
|
|
auto constexpr kSizePerHead = 104;
|
|
} // namespace
|
|
|
|
namespace mmha
|
|
{
|
|
|
|
#ifndef FAST_BUILD // skip mmha_104 for fast build
|
|
#ifdef ENABLE_BF16
|
|
INSTANTIATE_MMHA_LAUNCHERS(__nv_bfloat16, kSizePerHead)
|
|
#endif // ENABLE_BF16
|
|
#endif // FAST_BUILD
|
|
|
|
} // namespace mmha
|
|
|
|
} // namespace kernels
|
|
} // namespace tensorrt_llm
|