mirror of
https://github.com/NVIDIA/TensorRT-LLM.git
synced 2026-01-14 06:27:45 +08:00
75057cd036
* Update TensorRT-LLM --------- Co-authored-by: Puneesh Khanna <puneesh.khanna@tii.ae> Co-authored-by: Ethan Zhang <26497102+ethnzhng@users.noreply.github.com>
30 lines
997 B
Plaintext
30 lines
997 B
Plaintext
/*
|
|
* Copyright (c) 2022-2024, 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 "tensorrt_llm/kernels/weightOnlyBatchedGemv/kernelDispatcher.h"
|
|
|
|
namespace tensorrt_llm
|
|
{
|
|
namespace kernels
|
|
{
|
|
namespace weight_only
|
|
{
|
|
INSTANTIATE_WEIGHT_ONLY_CUDA_DISPATCHERS(
|
|
KernelType::FP16Int8Groupwise, FP16DetailsA, Int8DetailsW, ColumnMajorInterleaved, true, 64);
|
|
} // namespace weight_only
|
|
} // namespace kernels
|
|
} // namespace tensorrt_llm
|