mirror of
https://github.com/PaddlePaddle/FastDeploy.git
synced 2025-12-24 13:28:13 +08:00
35 lines
1.6 KiB
Plaintext
35 lines
1.6 KiB
Plaintext
FROM registry.baidubce.com/paddlepaddle/fastdeploy:llm-base-gcc12.3-cuda12.3-cudnn9-nccl2.15.5
|
|
|
|
WORKDIR /opt/output/
|
|
COPY ./server/ /opt/output/Serving/
|
|
COPY ./client/ /opt/output/client/
|
|
|
|
ENV LD_LIBRARY_PATH="/usr/local/cuda-12.3/compat/:$LD_LIBRARY_PATH"
|
|
|
|
RUN pip config set global.index-url https://pypi.tuna.tsinghua.edu.cn/simple
|
|
RUN python3 -m pip install --pre paddlepaddle-gpu -i https://www.paddlepaddle.org.cn/packages/nightly/cu123/ \
|
|
&& python3 -m pip install paddlenlp==3.0.0b0 \
|
|
&& python3 -m pip install --no-cache-dir sentencepiece pycryptodome tritonclient[all]==2.41.1
|
|
|
|
RUN git clone https://gitee.com/paddlepaddle/PaddleNLP.git && cd PaddleNLP/csrc \
|
|
&& python3 setup_cuda.py build && python3 setup_cuda.py install --user \
|
|
&& cp -r /opt/output/PaddleNLP/paddlenlp /usr/local/lib/python3.10/dist-packages/ \
|
|
&& cp -r /root/.local/lib/python3.10/site-packages/* /usr/local/lib/python3.10/dist-packages/ \
|
|
&& rm -rf /opt/output/PaddleNLP
|
|
|
|
RUN cd /opt/output/client && pip install -r requirements.txt && pip install .
|
|
|
|
RUN python3 -m pip install -r /opt/output/Serving/requirements.txt && rm /opt/output/Serving/requirements.txt
|
|
RUN mv Serving/server /usr/local/lib/python3.10/dist-packages/
|
|
RUN mkdir -p /opt/output/Serving/llm_model/model/1 \
|
|
&& mv /opt/output/Serving/config/config.pbtxt /opt/output/Serving/llm_model/model/ \
|
|
&& rm -rf /opt/output/Serving/config/
|
|
RUN echo "from server.triton_server import TritonPythonModel" >>/opt/output/Serving/llm_model/model/1/model.py
|
|
|
|
RUN cd /opt/output/Serving/ \
|
|
&& cp scripts/start_server.sh . && cp scripts/stop_server.sh . \
|
|
&& rm -rf scripts
|
|
|
|
ENV http_proxy=""
|
|
ENV https_proxy=""
|