b2e89e6e80
[FT] feat: Add FasterTransformer v3.0 1. Add supporting of INT8 quantization of cpp and TensorFlow op. 2. Provide the tools to quantize the model. 3. Fix the bugs that cmake 3.15 and 3.16 cannot build this project. 4. Deprecate the FasterTransformer v1
35 lines
1.3 KiB
CMake
35 lines
1.3 KiB
CMake
# Copyright (c) 2020, 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.
|
|
cmake_minimum_required(VERSION 3.8)
|
|
|
|
set(encoder_sample_files
|
|
encoder_sample.cc
|
|
)
|
|
|
|
set(decoding_beamsearch_sample_files
|
|
decoding_beamsearch_sample.cc
|
|
)
|
|
|
|
set(decoding_sampling_sample_files
|
|
decoding_sampling_sample.cc
|
|
)
|
|
|
|
add_executable(encoder_sample ${encoder_sample_files})
|
|
target_link_libraries(encoder_sample PUBLIC -lcublas -lcudart encoder)
|
|
|
|
add_executable(decoding_beamsearch_sample ${decoding_beamsearch_sample_files})
|
|
target_link_libraries(decoding_beamsearch_sample PUBLIC -lcublas -lcudart decoder decoding)
|
|
|
|
add_executable(decoding_sampling_sample ${decoding_sampling_sample_files})
|
|
target_link_libraries(decoding_sampling_sample PUBLIC -lcublas -lcudart -lcurand decoder decoding) |