Skip to content

add xpu p800 release dockerfile #10552

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

Merged
merged 1 commit into from
May 12, 2025
Merged

add xpu p800 release dockerfile #10552

Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
42 changes: 42 additions & 0 deletions llm/server/dockerfiles/Dockerfile_serving_xpu_p800
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,42 @@
FROM registry.baidubce.com/paddlepaddle/fastdeploy:llm-base-gcc12.3-cuda12.4-cudnn9-nccl2.15.5

ENV http_proxy=http://agent.baidu.com:8891
ENV https_proxy=http://agent.baidu.com:8891
ENV no_proxy=localhost,bj.bcebos.com,su.bcebos.com,pypi.tuna.tsinghua.edu.cn,paddle-ci.gz.bcebos.com

WORKDIR /opt/output/

# 安装 paddlepaddle & paddlenlp & paddlenlp_ops
RUN pip config set global.index-url https://mirrors.tuna.tsinghua.edu.cn/pypi/web/simple \
&& python3 -m pip install -U --no-deps --force-reinstall https://paddle-whl.bj.bcebos.com/nightly/xpu-p800/paddlepaddle-xpu/paddlepaddle_xpu-3.0.0.dev20250426-cp310-cp310-linux_x86_64.whl \
&& python3 -m pip install --no-cache-dir sentencepiece pycryptodome tritonclient[all]==2.41.1 \
&& apt update && apt install net-tools \
&& apt-get clean && rm -rf /var/lib/apt/lists/*

# clone paddle & paddlenlp 源码（代码版本应与上述安装版本对齐）
RUN mkdir -p /opt/source/ && cd /opt/source/ \
&& git clone https://github.com/PaddlePaddle/Paddle.git \
&& python3 -m pip install --no-cache-dir -r Paddle/python/requirements.txt \
&& git clone https://github.com/PaddlePaddle/PaddleNLP.git && cd PaddleNLP && git checkout 323ffec4fad74b5df9b8f6c2ec37d6855f6e62ca && cd ..\
&& 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

# 安装 paddlenlp_ops
RUN cd /opt/source/ && wget https://paddlenlp.bj.bcebos.com/xpu_release/xpu_release/paddlenlp_ops_xpu.tar.gz \
&& mkdir -p paddlenlp_ops_xpu && tar zxf paddlenlp_ops_xpu.tar.gz -C paddlenlp_ops_xpu \
&& cd paddlenlp_ops_xpu/src && python3 setup.py install \
&& rm -f paddlenlp_ops_xpu.tar.gz

RUN cp /opt/source/PaddleNLP/llm/server/server/scripts/start_server.sh start_server \
&& chmod +x start_server \
&& mv start_server /usr/local/bin/ \
&& cp /opt/source/PaddleNLP/llm/server/server/scripts/stop_server.sh stop_server \
&& chmod +x stop_server \
&& mv stop_server /usr/local/bin/

# RUN cp /opt/source/PaddleNLP/llm/server/server/server/download_model.py download_model.py

ENV PYTHONPATH="/opt/source/PaddleNLP/llm/server/server:/opt/source/PaddleNLP"

ENV http_proxy=""
ENV https_proxy=""