diff --git a/python/examples/pipeline/PaddleDetection/faster_rcnn/config.yml b/python/examples/pipeline/PaddleDetection/faster_rcnn/config.yml index 0bcb6c288914acc852c82974eb7eacf560784255..891b4b997c2ebb98d6694464b5dbe0532c01145c 100644 --- a/python/examples/pipeline/PaddleDetection/faster_rcnn/config.yml +++ b/python/examples/pipeline/PaddleDetection/faster_rcnn/config.yml @@ -1,18 +1,29 @@ dag: + #op资源类型, True, 为线程模型；False，为进程模型 is_thread_op: false + #使用性能分析, True，生成Timeline性能数据，对性能有一定影响；False为不使用 tracer: interval_s: 30 +#http端口, rpc_port和http_port不允许同时为空。当rpc_port可用且http_port为空时，不自动生成http_port http_port: 18082 op: faster_rcnn: + #并发数，is_thread_op=True时，为线程并发；否则为进程并发 concurrency: 2 - local_service_conf: + #client类型，包括brpc, grpc和local_predictor.local_predictor不启动Serving服务，进程内预测 client_type: local_predictor + # device_type, 0=cpu, 1=gpu, 2=tensorRT, 3=arm cpu, 4=kunlun xpu device_type: 1 + #计算硬件ID，当devices为""或不写时为CPU预测；当devices为"0", "0,1,2"时为GPU预测，表示使用的GPU卡 devices: '2' + #Fetch结果列表，以bert_seq128_model中fetch_var的alias_name为准, 如果没有设置则全部返回 fetch_list: - save_infer_model/scale_0.tmp_1 + #模型路径 model_config: serving_server/ +#rpc端口, rpc_port和http_port不允许同时为空。当rpc_port为空且http_port不为空时，会自动将rpc_port设置为http_port+1 rpc_port: 9998 +#worker_num, 最大并发数。当build_dag_each_worker=True时, 框架会创建worker_num个进程，每个进程内构建grpcSever和DAG +#当build_dag_each_worker=False时，框架会设置主线程grpc线程池的max_workers=worker_num worker_num: 20 diff --git a/python/examples/pipeline/PaddleDetection/ppyolo_mbv3/config.yml b/python/examples/pipeline/PaddleDetection/ppyolo_mbv3/config.yml index 0476d4ce6554af31e21d0c2ea0473e23de18523f..71e93f39c7979522e73058af7fa2969575b5129c 100644 --- a/python/examples/pipeline/PaddleDetection/ppyolo_mbv3/config.yml +++ b/python/examples/pipeline/PaddleDetection/ppyolo_mbv3/config.yml @@ -1,18 +1,30 @@ dag: + #op资源类型, True, 为线程模型；False，为进程模型 is_thread_op: false + #使用性能分析, True，生成Timeline性能数据，对性能有一定影响；False为不使用 tracer: interval_s: 30 +#http端口, rpc_port和http_port不允许同时为空。当rpc_port可用且http_port为空时，不自动生成http_port http_port: 18082 op: ppyolo_mbv3: + #并发数，is_thread_op=True时，为线程并发；否则为进程并发 concurrency: 10 local_service_conf: + #client类型，包括brpc, grpc和local_predictor.local_predictor不启动Serving服务，进程内预测 client_type: local_predictor + # device_type, 0=cpu, 1=gpu, 2=tensorRT, 3=arm cpu, 4=kunlun xpu device_type: 1 + #计算硬件ID，当devices为""或不写时为CPU预测；当devices为"0", "0,1,2"时为GPU预测，表示使用的GPU卡 devices: '2' + #Fetch结果列表，以bert_seq128_model中fetch_var的alias_name为准, 如果没有设置则全部返回 fetch_list: - save_infer_model/scale_0.tmp_1 + #模型路径 model_config: serving_server/ +#rpc端口, rpc_port和http_port不允许同时为空。当rpc_port为空且http_port不为空时，会自动将rpc_port设置为http_port+1 rpc_port: 9998 +#worker_num, 最大并发数。当build_dag_each_worker=True时, 框架会创建worker_num个进程，每个进程内构建grpcSever和DAG +#当build_dag_each_worker=False时，框架会设置主线程grpc线程池的max_workers=worker_num worker_num: 20 diff --git a/python/examples/pipeline/PaddleDetection/yolov3/config.yml b/python/examples/pipeline/PaddleDetection/yolov3/config.yml index 20653280736316c87d50786e76db5ba842040525..0f6d839edd3467e4dca203b9a21db850db3f4d5e 100644 --- a/python/examples/pipeline/PaddleDetection/yolov3/config.yml +++ b/python/examples/pipeline/PaddleDetection/yolov3/config.yml @@ -1,18 +1,29 @@ dag: + #op资源类型, True, 为线程模型；False，为进程模型 is_thread_op: false + #使用性能分析, True，生成Timeline性能数据，对性能有一定影响；False为不使用 tracer: interval_s: 30 +#http端口, rpc_port和http_port不允许同时为空。当rpc_port可用且http_port为空时，不自动生成http_port http_port: 18082 op: yolov3: + #并发数，is_thread_op=True时，为线程并发；否则为进程并发 concurrency: 10 - local_service_conf: + #client类型，包括brpc, grpc和local_predictor.local_predictor不启动Serving服务，进程内预测 client_type: local_predictor + # device_type, 0=cpu, 1=gpu, 2=tensorRT, 3=arm cpu, 4=kunlun xpu device_type: 1 + #计算硬件ID，当devices为""或不写时为CPU预测；当devices为"0", "0,1,2"时为GPU预测，表示使用的GPU卡 devices: '2' + #Fetch结果列表，以bert_seq128_model中fetch_var的alias_name为准, 如果没有设置则全部返回 fetch_list: - save_infer_model/scale_0.tmp_1 + #模型路径 model_config: serving_server/ +#rpc端口, rpc_port和http_port不允许同时为空。当rpc_port为空且http_port不为空时，会自动将rpc_port设置为http_port+1 rpc_port: 9998 +#worker_num, 最大并发数。当build_dag_each_worker=True时, 框架会创建worker_num个进程，每个进程内构建grpcSever和DAG +#当build_dag_each_worker=False时，框架会设置主线程grpc线程池的max_workers=worker_num worker_num: 20 diff --git a/python/examples/pipeline/bert/config.yml b/python/examples/pipeline/bert/config.yml index a2b39264dd78ccb8f2936c7bd603d1c3d57b2574..5f1226646bb1a14fee3460bc98e25321b6aaa27a 100644 --- a/python/examples/pipeline/bert/config.yml +++ b/python/examples/pipeline/bert/config.yml @@ -1,17 +1,32 @@ +#worker_num, 最大并发数。当build_dag_each_worker=True时, 框架会创建worker_num个进程，每个进程内构建grpcSever和DAG +##当build_dag_each_worker=False时，框架会设置主线程grpc线程池的max_workers=worker_num worker_num: 20 +#build_dag_each_worker, False，框架在进程内创建一条DAG；True，框架会每个进程内创建多个独立的DAG +build_dag_each_worker: false + dag: + #op资源类型, True, 为线程模型；False，为进程模型 is_thread_op: false + #使用性能分析, True，生成Timeline性能数据，对性能有一定影响；False为不使用 tracer: interval_s: 10 +#http端口, rpc_port和http_port不允许同时为空。当rpc_port可用且http_port为空时，不自动生成http_port http_port: 18082 +#rpc端口, rpc_port和http_port不允许同时为空。当rpc_port为空且http_port不为空时，会自动将rpc_port设置为http_port+1 rpc_port: 9998 op: bert: + #并发数，is_thread_op=True时，为线程并发；否则为进程并发 concurrency: 2 - + #当op配置没有server_endpoints时，从local_service_conf读取本地服务配置 local_service_conf: + #client类型，包括brpc, grpc和local_predictor.local_predictor不启动Serving服务，进程内预测 client_type: local_predictor + # device_type, 0=cpu, 1=gpu, 2=tensorRT, 3=arm cpu, 4=kunlun xpu device_type: 1 + #计算硬件ID，当devices为""或不写时为CPU预测；当devices为"0", "0,1,2"时为GPU预测，表示使用的GPU卡 devices: '2' + #Fetch结果列表，以bert_seq128_model中fetch_var的alias_name为准, 如果没有设置则全部返回 fetch_list: + #bert模型路径 model_config: bert_seq128_model/ diff --git a/python/examples/pipeline/ocr/config.yml b/python/examples/pipeline/ocr/config.yml index 58e3ed54d5d286290ff4846364c2393af427bd9d..2767fa77ceaa975c4e20bedaaf13ffa0e2b35de3 100644 --- a/python/examples/pipeline/ocr/config.yml +++ b/python/examples/pipeline/ocr/config.yml @@ -38,6 +38,9 @@ op: #Fetch结果列表，以client_config中fetch_var的alias_name为准 fetch_list: ["concat_1.tmp_0"] + + # device_type, 0=cpu, 1=gpu, 2=tensorRT, 3=arm cpu, 4=kunlun xpu + device_type: 0 #计算硬件ID，当devices为""或不写时为CPU预测；当devices为"0", "0,1,2"时为GPU预测，表示使用的GPU卡 devices: "" @@ -71,6 +74,8 @@ op: #Fetch结果列表，以client_config中fetch_var的alias_name为准 fetch_list: ["ctc_greedy_decoder_0.tmp_0", "softmax_0.tmp_0"] + # device_type, 0=cpu, 1=gpu, 2=tensorRT, 3=arm cpu, 4=kunlun xpu + device_type: 0 #计算硬件ID，当devices为""或不写时为CPU预测；当devices为"0", "0,1,2"时为GPU预测，表示使用的GPU卡 devices: "" diff --git a/tools/Dockerfile.cuda10.1-cudnn7.devel b/tools/Dockerfile.cuda10.1-cudnn7.devel index 24087af9490b8b5f4b7f57d70cb927c580da6066..1ed462ec4c1df845bc461577d97c3fee7d5852d6 100644 --- a/tools/Dockerfile.cuda10.1-cudnn7.devel +++ b/tools/Dockerfile.cuda10.1-cudnn7.devel @@ -83,7 +83,7 @@ RUN ln -sf /usr/local/bin/python3.6 /usr/local/bin/python3 && ln -sf /usr/local/ RUN rm -r /root/python_build # Install Go and glide -RUN wget -qO- https://dl.google.com/go/go1.14.linux-amd64.tar.gz | \ +RUN wget -qO- https://paddle-ci.cdn.bcebos.com/go1.17.2.linux-amd64.tar.gz | \ tar -xz -C /usr/local && \ mkdir /root/go && \ mkdir /root/go/bin && \ diff --git a/tools/Dockerfile.cuda10.2-cudnn7.devel b/tools/Dockerfile.cuda10.2-cudnn7.devel index 6425a7a39ec1ca84a3f4d5ab305bcb6b413862bc..eee59b6e43ac18fc645dfb9c8399b33dff9f0e6d 100644 --- a/tools/Dockerfile.cuda10.2-cudnn7.devel +++ b/tools/Dockerfile.cuda10.2-cudnn7.devel @@ -83,7 +83,7 @@ RUN ln -sf /usr/local/bin/python3.6 /usr/local/bin/python3 && ln -sf /usr/local/ RUN rm -r /root/python_build # Install Go and glide -RUN wget -qO- https://dl.google.com/go/go1.14.linux-amd64.tar.gz | \ +RUN wget -qO- https://paddle-ci.cdn.bcebos.com/go1.17.2.linux-amd64.tar.gz | \ tar -xz -C /usr/local && \ mkdir /root/go && \ mkdir /root/go/bin && \ diff --git a/tools/Dockerfile.cuda10.2-cudnn8.devel b/tools/Dockerfile.cuda10.2-cudnn8.devel index d07731343bb9bfd28f59dd4dcf240bcb26d302f5..5ba14c77c3ed3f479db5e05e9c9fbc8e6468dab6 100644 --- a/tools/Dockerfile.cuda10.2-cudnn8.devel +++ b/tools/Dockerfile.cuda10.2-cudnn8.devel @@ -83,7 +83,7 @@ RUN ln -sf /usr/local/bin/python3.6 /usr/local/bin/python3 && ln -sf /usr/local/ RUN rm -r /root/python_build # Install Go and glide -RUN wget -qO- https://dl.google.com/go/go1.14.linux-amd64.tar.gz | \ +RUN wget -qO- https://paddle-ci.cdn.bcebos.com/go1.17.2.linux-amd64.tar.gz | \ tar -xz -C /usr/local && \ mkdir /root/go && \ mkdir /root/go/bin && \ diff --git a/tools/Dockerfile.cuda11.2-cudnn8.devel b/tools/Dockerfile.cuda11.2-cudnn8.devel new file mode 100644 index 0000000000000000000000000000000000000000..363096b1ddd48268275992941c740c9d8d34e868 --- /dev/null +++ b/tools/Dockerfile.cuda11.2-cudnn8.devel @@ -0,0 +1,147 @@ +# A image for building paddle binaries +# Use cuda devel base image for both cpu and gpu environment +# When you modify it, please be aware of cudnn-runtime version +FROM nvidia/cuda:11.2.0-cudnn8-devel-ubuntu16.04 +MAINTAINER PaddlePaddle Authors + +# ENV variables +ARG WITH_GPU +ARG WITH_AVX + +ENV WITH_GPU=${WITH_GPU:-ON} +ENV WITH_AVX=${WITH_AVX:-ON} + +ENV HOME /root +# Add bash enhancements +COPY tools/dockerfiles/root/ /root/ + +# Prepare packages for Python +RUN apt-get update && \ + apt-get install -y make build-essential libssl-dev zlib1g-dev libbz2-dev \ + libreadline-dev libsqlite3-dev wget curl llvm libncurses5-dev libncursesw5-dev \ + xz-utils tk-dev libffi-dev liblzma-dev + +RUN apt-get update && \ + apt-get install -y --allow-downgrades --allow-change-held-packages \ + patchelf git python-pip python-dev python-opencv openssh-server bison \ + wget unzip unrar tar xz-utils bzip2 gzip coreutils ntp \ + curl sed grep graphviz libjpeg-dev zlib1g-dev \ + python-matplotlib unzip \ + automake locales clang-format swig \ + liblapack-dev liblapacke-dev libcurl4-openssl-dev \ + net-tools libtool module-init-tools vim && \ + apt-get clean -y + +RUN ln -s /usr/lib/x86_64-linux-gnu/libssl.so /usr/lib/libssl.so.10 && \ + ln -s /usr/lib/x86_64-linux-gnu/libcrypto.so /usr/lib/libcrypto.so.10 + +RUN wget https://github.com/koalaman/shellcheck/releases/download/v0.7.1/shellcheck-v0.7.1.linux.x86_64.tar.xz -O shellcheck-v0.7.1.linux.x86_64.tar.xz && \ + tar -xf shellcheck-v0.7.1.linux.x86_64.tar.xz && cp shellcheck-v0.7.1/shellcheck /usr/bin/shellcheck && \ + rm -rf shellcheck-v0.7.1.linux.x86_64.tar.xz shellcheck-v0.7.1 + +# Downgrade gcc&&g++ +WORKDIR /usr/bin + COPY tools/dockerfiles/build_scripts /build_scripts + RUN bash /build_scripts/install_gcc.sh gcc82 && rm -rf /build_scripts + RUN cp gcc gcc.bak && cp g++ g++.bak && rm gcc && rm g++ + RUN ln -s /usr/local/gcc-8.2/bin/gcc /usr/local/bin/gcc + RUN ln -s /usr/local/gcc-8.2/bin/g++ /usr/local/bin/g++ + RUN ln -s /usr/local/gcc-8.2/bin/gcc /usr/bin/gcc + RUN ln -s /usr/local/gcc-8.2/bin/g++ /usr/bin/g++ + ENV PATH=/usr/local/gcc-8.2/bin:$PATH + +# install cmake +WORKDIR /home +RUN wget -q https://cmake.org/files/v3.16/cmake-3.16.0-Linux-x86_64.tar.gz && tar -zxvf cmake-3.16.0-Linux-x86_64.tar.gz && rm cmake-3.16.0-Linux-x86_64.tar.gz +ENV PATH=/home/cmake-3.16.0-Linux-x86_64/bin:$PATH + +# Install Python3.6 +RUN mkdir -p /root/python_build/ && wget -q https://www.sqlite.org/2018/sqlite-autoconf-3250300.tar.gz && \ + tar -zxf sqlite-autoconf-3250300.tar.gz && cd sqlite-autoconf-3250300 && \ + ./configure -prefix=/usr/local && make -j8 && make install && cd ../ && rm sqlite-autoconf-3250300.tar.gz + +RUN wget -q https://www.python.org/ftp/python/3.6.0/Python-3.6.0.tgz && \ + tar -xzf Python-3.6.0.tgz && cd Python-3.6.0 && \ + CFLAGS="-Wformat" ./configure --prefix=/usr/local/ --enable-shared > /dev/null && \ + make -j8 > /dev/null && make altinstall > /dev/null && ldconfig && cd .. && rm -rf Python-3.6.0* + +# Install Python3.7 +RUN wget -q https://www.python.org/ftp/python/3.7.0/Python-3.7.0.tgz && \ + tar -xzf Python-3.7.0.tgz && cd Python-3.7.0 && \ + CFLAGS="-Wformat" ./configure --prefix=/usr/local/ --enable-shared > /dev/null && \ + make -j8 > /dev/null && make altinstall > /dev/null && ldconfig && cd .. && rm -rf Python-3.7.0* + +# Install Python3.8 +RUN wget -q https://www.python.org/ftp/python/3.8.0/Python-3.8.0.tgz && \ + tar -xzf Python-3.8.0.tgz && cd Python-3.8.0 && \ + CFLAGS="-Wformat" ./configure --prefix=/usr/local/ --enable-shared > /dev/null && \ + make -j8 > /dev/null && make altinstall > /dev/null && ldconfig && cd .. && rm -rf Python-3.8.0* + +ENV LD_LIBRARY_PATH=/usr/local/lib:${LD_LIBRARY_PATH} +RUN ln -sf /usr/local/bin/python3.6 /usr/local/bin/python3 && ln -sf /usr/local/bin/python3.6 /usr/bin/python3 && ln -sf /usr/local/bin/pip3.6 /usr/local/bin/pip3 && ln -sf /usr/local/bin/pip3.6 /usr/bin/pip3 + +RUN rm -r /root/python_build + +# Install Go and glide +RUN wget -qO- https://paddle-ci.cdn.bcebos.com/go1.17.2.linux-amd64.tar.gz | \ + tar -xz -C /usr/local && \ + mkdir /root/go && \ + mkdir /root/go/bin && \ + mkdir /root/go/src && \ + echo "GOROOT=/usr/local/go" >> /root/.bashrc && \ + echo "GOPATH=/root/go" >> /root/.bashrc && \ + echo "PATH=/usr/local/go/bin:/root/go/bin:$PATH" >> /root/.bashrc +ENV GOROOT=/usr/local/go GOPATH=/root/go +# should not be in the same line with GOROOT definition, otherwise docker build could not find GOROOT. +ENV PATH=usr/local/go/bin:/root/go/bin:${PATH} + +# Install TensorRT +# following TensorRT.tar.gz is not the default official one, we do two miny changes: +# 1. Remove the unnecessary files to make the library small. TensorRT.tar.gz only contains include and lib now, +# and its size is only one-third of the official one. +# 2. Manually add ~IPluginFactory() in IPluginFactory class of NvInfer.h, otherwise, it couldn't work in paddle. +# See https://github.com/PaddlePaddle/Paddle/issues/10129 for details. + +# Downgrade TensorRT +COPY tools/dockerfiles/build_scripts /build_scripts +RUN bash /build_scripts/install_trt.sh cuda11.2 +RUN rm -rf /build_scripts + +# git credential to skip password typing +RUN git config --global credential.helper store + +# Fix locales to en_US.UTF-8 +RUN localedef -i en_US -f UTF-8 en_US.UTF-8 + +RUN apt-get install libprotobuf-dev -y + +# Older versions of patchelf limited the size of the files being processed and were fixed in this pr. +# https://github.com/NixOS/patchelf/commit/ba2695a8110abbc8cc6baf0eea819922ee5007fa +# So install a newer version here. +RUN wget -q https://paddle-ci.cdn.bcebos.com/patchelf_0.10-2_amd64.deb && \ + dpkg -i patchelf_0.10-2_amd64.deb + +# Configure OpenSSH server. c.f. https://docs.docker.com/engine/examples/running_ssh_service +RUN mkdir /var/run/sshd && echo 'root:root' | chpasswd && sed -ri 's/^PermitRootLogin\s+.*/PermitRootLogin yes/' /etc/ssh/sshd_config && sed -ri 's/UsePAM yes/#UsePAM yes/g' /etc/ssh/sshd_config +CMD source ~/.bashrc + +# ccache 3.7.9 +RUN wget https://paddle-ci.gz.bcebos.com/ccache-3.7.9.tar.gz && \ + tar xf ccache-3.7.9.tar.gz && mkdir /usr/local/ccache-3.7.9 && cd ccache-3.7.9 && \ + ./configure -prefix=/usr/local/ccache-3.7.9 && \ + make -j8 && make install && \ + ln -s /usr/local/ccache-3.7.9/bin/ccache /usr/local/bin/ccache + +RUN python3.8 -m pip install --upgrade pip==21.1.1 requests && \ + python3.7 -m pip install --upgrade pip==21.1.1 requests && \ + python3.6 -m pip install --upgrade pip==21.1.1 requests + +RUN wget https://paddle-serving.bj.bcebos.com/others/centos_ssl.tar && \ + tar xf centos_ssl.tar && rm -rf centos_ssl.tar && \ + mv libcrypto.so.1.0.2k /usr/lib/libcrypto.so.1.0.2k && mv libssl.so.1.0.2k /usr/lib/libssl.so.1.0.2k && \ + ln -sf /usr/lib/libcrypto.so.1.0.2k /usr/lib/libcrypto.so.10 && \ + ln -sf /usr/lib/libssl.so.1.0.2k /usr/lib/libssl.so.10 && \ + ln -sf /usr/lib/libcrypto.so.10 /usr/lib/libcrypto.so && \ + ln -sf /usr/lib/libssl.so.10 /usr/lib/libssl.so + +EXPOSE 22 diff --git a/tools/Dockerfile.devel b/tools/Dockerfile.devel index be31b2e9abd90f644eb0f94a6d672639e4b7f6c5..287759e8f82f3fc37200bb791a1bd6530ab6516e 100644 --- a/tools/Dockerfile.devel +++ b/tools/Dockerfile.devel @@ -83,7 +83,7 @@ RUN ln -sf /usr/local/bin/python3.6 /usr/local/bin/python3 && ln -sf /usr/local/ RUN rm -r /root/python_build # Install Go and glide -RUN wget -qO- https://dl.google.com/go/go1.14.linux-amd64.tar.gz | \ +RUN wget -qO- https://paddle-ci.cdn.bcebos.com/go1.17.2.linux-amd64.tar.gz | \ tar -xz -C /usr/local && \ mkdir /root/go && \ mkdir /root/go/bin && \