mirror of
https://github.com/PaddlePaddle/FastDeploy.git
synced 2025-10-06 17:17:14 +08:00
eeae48deff
* faster_tokenizer->fast_tokenizer * ErnieFasterTokenizer->ErnieFastTokenizer * update the fastdeploy_init Co-authored-by: Jason <jiangjiajun@baidu.com>
49 lines
2.6 KiB
Docker
49 lines
2.6 KiB
Docker
# Copyright (c) 2022 PaddlePaddle Authors. 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.
|
|
|
|
FROM nvcr.io/nvidia/tritonserver:21.10-py3 as full
|
|
FROM nvcr.io/nvidia/tritonserver:21.10-py3-min
|
|
|
|
COPY --from=full /opt/tritonserver/bin/tritonserver /opt/tritonserver/bin/fastdeployserver
|
|
COPY --from=full /opt/tritonserver/lib /opt/tritonserver/lib
|
|
COPY --from=full /opt/tritonserver/include /opt/tritonserver/include
|
|
COPY --from=full /opt/tritonserver/backends/python /opt/tritonserver/backends/python
|
|
|
|
COPY serving/TensorRT-8.4.1.5 /opt/
|
|
|
|
ENV TZ=Asia/Shanghai \
|
|
DEBIAN_FRONTEND=noninteractive \
|
|
DCGM_VERSION=2.2.9
|
|
RUN apt-get update \
|
|
&& apt-key del 7fa2af80 \
|
|
&& wget https://developer.download.nvidia.com/compute/cuda/repos/ubuntu2004/x86_64/cuda-keyring_1.0-1_all.deb \
|
|
&& dpkg -i cuda-keyring_1.0-1_all.deb \
|
|
&& apt-key adv --fetch-keys https://developer.download.nvidia.com/compute/cuda/repos/ubuntu2004/x86_64/7fa2af80.pub \
|
|
&& apt-get update && apt-get install -y --no-install-recommends datacenter-gpu-manager=1:2.2.9
|
|
|
|
RUN apt-get update \
|
|
&& apt-get install -y --no-install-recommends libre2-5 libb64-0d python3 python3-pip libarchive-dev ffmpeg libsm6 libxext6 \
|
|
&& python3 -m pip install -U pip \
|
|
&& python3 -m pip install paddlepaddle-gpu paddlenlp fast-tokenizer-python
|
|
|
|
COPY python/dist/*.whl /opt/fastdeploy/
|
|
RUN python3 -m pip install /opt/fastdeploy/*.whl \
|
|
&& rm -rf /opt/fastdeploy/*.whl
|
|
|
|
COPY serving/build/libtriton_fastdeploy.so /opt/tritonserver/backends/fastdeploy/
|
|
COPY build/fastdeploy_install /opt/fastdeploy/
|
|
|
|
ENV LD_LIBRARY_PATH="/opt/TensorRT-8.4.1.5/lib/:/opt/fastdeploy/lib:/opt/fastdeploy/third_libs/install/onnxruntime/lib:/opt/fastdeploy/third_libs/install/paddle2onnx/lib:/opt/fastdeploy/third_libs/install/tensorrt/lib:/opt/fastdeploy/third_libs/install/paddle_inference/paddle/lib:/opt/fastdeploy/third_libs/install/paddle_inference/third_party/install/mkldnn/lib:/opt/fastdeploy/third_libs/install/paddle_inference/third_party/install/mklml/lib:/opt/fastdeploy/third_libs/install/openvino/runtime/lib:$LD_LIBRARY_PATH"
|
|
ENV PATH="/opt/tritonserver/bin:$PATH"
|