Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

[LLM] update llm server dockerfiles #9771

Open
wants to merge 2 commits into
base: develop
Choose a base branch
from
Open

[LLM] update llm server dockerfiles #9771

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
e7b4800
[LLM] update llm server dockerfiles
kevincheng2 Jan 11, 2025
d24e2ef
Merge branch 'PaddlePaddle:develop' into develop
kevincheng2 Jan 16, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
33 changes: 15 additions & 18 deletions llm/server/dockerfiles/Dockerfile_serving_cuda118_cudnn8
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,31 +1,28 @@
FROM registry.baidubce.com/paddlepaddle/fastdeploy:llm-base-gcc12.3-cuda11.8-cudnn8-nccl2.15.5

WORKDIR /opt/output/
COPY ./server/ /opt/output/Serving/

ENV LD_LIBRARY_PATH="/usr/local/cuda-11.8/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/cu118/ \
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
&& python3 -m pip install --no-cache-dir sentencepiece pycryptodome tritonclient[all]==2.41.1 \
&& python3 -m pip install --no-cache-dir --force-reinstall https://paddlepaddle-inference-banchmark.bj.bcebos.com/paddlenlp_ops-0.0.0-py3-none-any.whl \
&& apt-get clean && rm -rf /var/lib/apt/lists/*

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 mkdir -p /opt/source/ && cd /opt/source/ \
&& git clone https://github.com/PaddlePaddle/Paddle.git \
&& git clone https://github.com/PaddlePaddle/PaddleNLP.git \
&& cp -r /opt/source/PaddleNLP/paddlenlp /usr/local/lib/python3.10/dist-packages/ \
&& python3 -m pip install --no-cache-dir -r PaddleNLP/requirements.txt \
&& python3 -m pip install --no-cache-dir -r PaddleNLP/llm/server/server/requirements.txt

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
&& cp /opt/source/PaddleNLP/llm/server/server/config/config.pbtxt /opt/output/Serving/llm_model/model/ \
&& cp /opt/source/PaddleNLP/llm/server/server/scripts/start_server.sh /opt/output/Serving/ \
&& cp /opt/source/PaddleNLP/llm/server/server/scripts/stop_server.sh /opt/output/Serving/

RUN cd /opt/output/Serving/ \
&& cp scripts/start_server.sh . && cp scripts/stop_server.sh . \
&& rm -rf scripts
ENV PYTHONPATH="/opt/source/PaddleNLP/llm/server/server"
RUN echo "from server.triton_server import TritonPythonModel" >>/opt/output/Serving/llm_model/model/1/model.py

ENV http_proxy=""
ENV https_proxy=""
31 changes: 14 additions & 17 deletions llm/server/dockerfiles/Dockerfile_serving_cuda123_cudnn9
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,31 +1,28 @@
FROM registry.baidubce.com/paddlepaddle/fastdeploy:llm-base-gcc12.3-cuda12.3-cudnn9-nccl2.15.5

WORKDIR /opt/output/
COPY ./server/ /opt/output/Serving/

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
&& python3 -m pip install --no-cache-dir sentencepiece pycryptodome tritonclient[all]==2.41.1 \
&& python3 -m pip install --no-cache-dir --force-reinstall https://paddlepaddle-inference-banchmark.bj.bcebos.com/paddlenlp_ops-0.0.0-py3-none-any.whl \
&& apt-get clean && rm -rf /var/lib/apt/lists/*

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 mkdir -p /opt/source/ && cd /opt/source/ \
&& git clone https://github.com/PaddlePaddle/Paddle.git \
&& git clone https://github.com/PaddlePaddle/PaddleNLP.git \
&& cp -r /opt/source/PaddleNLP/paddlenlp /usr/local/lib/python3.10/dist-packages/ \
&& python3 -m pip install --no-cache-dir -r PaddleNLP/requirements.txt \
&& python3 -m pip install --no-cache-dir -r PaddleNLP/llm/server/server/requirements.txt

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
&& cp /opt/source/PaddleNLP/llm/server/server/config/config.pbtxt /opt/output/Serving/llm_model/model/ \
&& cp /opt/source/PaddleNLP/llm/server/server/scripts/start_server.sh /opt/output/Serving/ \
&& cp /opt/source/PaddleNLP/llm/server/server/scripts/stop_server.sh /opt/output/Serving/

RUN cd /opt/output/Serving/ \
&& cp scripts/start_server.sh . && cp scripts/stop_server.sh . \
&& rm -rf scripts
ENV PYTHONPATH="/opt/source/PaddleNLP/llm/server/server"
RUN echo "from server.triton_server import TritonPythonModel" >>/opt/output/Serving/llm_model/model/1/model.py

ENV http_proxy=""
ENV https_proxy=""