mirror of
https://github.com/hiyouga/LLaMA-Factory.git
synced 2025-11-05 02:12:14 +08:00
13170577b2
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com> Co-authored-by: Yaowei Zheng <hiyouga@buaa.edu.cn>
78 lines
2.9 KiB
Docker
78 lines
2.9 KiB
Docker
# NVIDIA official image (ubuntu-22.04 + cuda-12.4 + python-3.10)
|
|
# https://docs.nvidia.com/deeplearning/frameworks/pytorch-release-notes/rel-24-08.html
|
|
FROM nvcr.io/nvidia/pytorch:24.05-py3
|
|
|
|
ENV DEBIAN_FRONTEND=noninteractive
|
|
ENV PIP_ROOT_USER_ACTION=ignore
|
|
ENV PYPI_MIRROR=https://mirrors.aliyun.com/pypi/simple/
|
|
ENV PYPI_TRUSTED_HOST=mirrors.aliyun.com
|
|
ENV APT_MIRROR=https://mirrors.tuna.tsinghua.edu.cn/ubuntu/
|
|
|
|
RUN pip install --upgrade pip setuptools wheel --trusted-host ${PYPI_TRUSTED_HOST} --index-url ${PYPI_MIRROR}
|
|
|
|
RUN pip uninstall -y torch torchvision torch-tensorrt \
|
|
flash_attn transformer-engine \
|
|
cudf dask-cuda cugraph cugraph-service-server cuml raft-dask cugraph-dgl cugraph-pyg dask-cudf
|
|
|
|
RUN pip install torch==2.6.0 torchvision==0.21.0 torchaudio==2.6.0 --index-url https://download.pytorch.org/whl/cu124
|
|
|
|
RUN pip uninstall -y opencv opencv-python opencv-python-headless && \
|
|
rm -rf /usr/local/lib/python3.10/dist-packages/cv2/ && \
|
|
pip install opencv-python-headless==4.11.0.86 --trusted-host ${PYPI_TRUSTED_HOST} --index-url ${PYPI_MIRROR}
|
|
|
|
RUN pip install "numpy==1.26.4" "optree>=0.13.0" "spacy==3.7.5" "weasel==0.4.1" \
|
|
transformer-engine[pytorch]==2.2.0 megatron-core==0.13.0 deepspeed==0.16.4 \
|
|
--trusted-host ${PYPI_TRUSTED_HOST} --index-url ${PYPI_MIRROR}
|
|
|
|
RUN pip install https://github.com/Dao-AILab/flash-attention/releases/download/v2.7.2.post1/flash_attn-2.7.2.post1+cu12torch2.6cxx11abiFALSE-cp310-cp310-linux_x86_64.whl
|
|
|
|
# RUN pip install vllm==0.8.4 \
|
|
# --trusted-host ${PYPI_TRUSTED_HOST} --index-url ${PYPI_MIRROR}
|
|
|
|
WORKDIR /build
|
|
|
|
ARG apex_url=git+https://github.com/NVIDIA/apex.git@25.04
|
|
RUN pip uninstall -y apex && \
|
|
MAX_JOBS=32 NINJA_FLAGS="-j32" NVCC_APPEND_FLAGS="--threads 32" \
|
|
pip install -v --disable-pip-version-check --no-cache-dir --no-build-isolation \
|
|
--config-settings "--build-option=--cpp_ext --cuda_ext --parallel 32" ${apex_url}
|
|
|
|
RUN rm -rf /build
|
|
WORKDIR /workspace
|
|
|
|
RUN cp /etc/apt/sources.list /etc/apt/sources.list.bak && \
|
|
{ \
|
|
echo "deb ${APT_MIRROR} jammy main restricted universe multiverse"; \
|
|
echo "deb ${APT_MIRROR} jammy-security main restricted universe multiverse"; \
|
|
echo "deb ${APT_MIRROR} jammy-updates main restricted universe multiverse"; \
|
|
echo "deb ${APT_MIRROR} jammy-backports main restricted universe multiverse"; \
|
|
} > /etc/apt/sources.list
|
|
|
|
RUN apt-get update && apt-get install -y zip
|
|
|
|
RUN apt-get install -y openjdk-21-jdk
|
|
ENV JAVA_HOME /usr/lib/jvm/java-21-openjdk-amd64
|
|
|
|
# pip install LLaMA-Factory
|
|
WORKDIR /app
|
|
|
|
COPY requirements.txt /app/
|
|
RUN pip install --no-cache-dir -r requirements.txt
|
|
|
|
RUN pip install "git+https://github.com/alibaba/roll.git#subdirectory=mcore_adapter"
|
|
|
|
COPY . /app/
|
|
RUN pip install -e ".[metrics]" --no-build-isolation
|
|
|
|
# Expose port 7860 for LLaMA Board
|
|
ENV GRADIO_SERVER_PORT=7860
|
|
EXPOSE 7860
|
|
|
|
# Expose port 8000 for API service
|
|
ENV API_PORT=8000
|
|
EXPOSE 8000
|
|
|
|
# unset proxy
|
|
ENV http_proxy=
|
|
ENV https_proxy=
|