Files
axolotl/docker/Dockerfile-base
2026-01-21 20:00:18 -05:00

93 lines
4.1 KiB
Plaintext

ARG CUDA_VERSION="11.8.0"
ARG CUDNN_VERSION="8"
ARG UBUNTU_VERSION="22.04"
ARG MAX_JOBS=4
ARG TARGETARCH
FROM nvidia/cuda:$CUDA_VERSION-cudnn$CUDNN_VERSION-devel-ubuntu$UBUNTU_VERSION AS base-builder
ENV PATH="/root/miniconda3/bin:${PATH}"
ARG TARGETARCH
ARG PYTHON_VERSION="3.11"
ARG PYTORCH_VERSION="2.1.2"
ARG CUDA="128"
ARG TORCH_CUDA_ARCH_LIST="7.0 7.5 8.0 8.6 9.0+PTX"
ENV PYTHON_VERSION=$PYTHON_VERSION
ENV TORCH_CUDA_ARCH_LIST=$TORCH_CUDA_ARCH_LIST
RUN apt-get update \
&& apt-get install -y --no-install-recommends \
wget git build-essential ninja-build git-lfs libaio-dev pkg-config \
ibverbs-providers ibverbs-utils infiniband-diags \
librdmacm-dev librdmacm1 rdmacm-utils slurm-wlm \
&& rm -rf /var/cache/apt/archives \
&& rm -rf /var/lib/apt/lists/* \
&& if [ "$TARGETARCH" = "amd64" ]; then \
MINICONDA_ARCH="x86_64"; \
elif [ "$TARGETARCH" = "arm64" ]; then \
MINICONDA_ARCH="aarch64"; \
else \
echo "Unsupported architecture: $TARGETARCH"; exit 1; \
fi \
&& wget https://repo.anaconda.com/miniconda/Miniconda3-latest-Linux-${MINICONDA_ARCH}.sh \
&& mkdir /root/.conda \
&& bash Miniconda3-latest-Linux-${MINICONDA_ARCH}.sh -b \
&& rm -f Miniconda3-latest-Linux-${MINICONDA_ARCH}.sh \
&& conda tos accept --override-channels --channel https://repo.anaconda.com/pkgs/main \
&& conda tos accept --override-channels --channel https://repo.anaconda.com/pkgs/r \
&& conda create -n "py${PYTHON_VERSION}" python="${PYTHON_VERSION}"
ENV PATH="/root/miniconda3/envs/py${PYTHON_VERSION}/bin:${PATH}"
WORKDIR /workspace
RUN python3 -m pip install --upgrade pip && pip3 install -U packaging==26.0 setuptools==75.8.0 wheel psutil && \
python3 -m pip install --no-cache-dir -U torch==${PYTORCH_VERSION}+cu${CUDA} torchvision --extra-index-url https://download.pytorch.org/whl/cu$CUDA && \
python3 -m pip cache purge
RUN if [ "$CUDA" != "130" ] ; then \
CAUSAL_CONV1D_FORCE_CXX11_ABI=TRUE CAUSAL_CONV1D_FORCE_BUILD=TRUE python3 -m pip install --no-cache-dir "causal_conv1d @ git+https://github.com/Dao-AILab/causal-conv1d.git@v1.5.4"; \
python3 -m pip install --no-cache-dir "mamba_ssm @ git+https://github.com/state-spaces/mamba.git@main"; \
python3 -m pip cache purge; \
fi
RUN git lfs install --skip-repo && \
pip3 install awscli && \
# The base image ships with `pydantic==1.8.2` which is not working
pip3 install -U --no-cache-dir pydantic==1.10.10 && \
pip3 cache purge
RUN case "$PYTORCH_VERSION" in \
2.9.[0-9]*) \
if [ "$CUDA" = "128" ]; then \
if [ "$TARGETARCH" = "amd64" ]; then \
WHL_FILE="flash_attn-2.8.3+cu128torch2.9-cp311-cp311-linux_x86_64.whl"; \
WHL_VERSION="v0.5.4"; \
elif [ "$TARGETARCH" = "arm64" ]; then \
WHL_FILE="flash_attn-2.8.3+cu128torch2.9-cp311-cp311-linux_aarch64.whl"; \
WHL_VERSION="v0.6.4"; \
else \
echo "Unsupported architecture: $TARGETARCH"; exit 1; \
fi; \
wget -nv https://github.com/mjun0812/flash-attention-prebuild-wheels/releases/download/${WHL_VERSION}/${WHL_FILE}; \
pip3 install --no-cache-dir ${WHL_FILE}; \
rm ${WHL_FILE}; \
elif [ "$CUDA" = "130" ]; then \
if [ "$TARGETARCH" = "amd64" ]; then \
WHL_FILE="flash_attn-2.8.3+cu130torch2.9-cp311-cp311-linux_x86_64.whl"; \
WHL_VERSION="v0.5.4"; \
elif [ "$TARGETARCH" = "arm64" ]; then \
WHL_FILE="flash_attn-2.8.3+cu130torch2.9-cp311-cp311-linux_aarch64.whl"; \
WHL_VERSION="v0.6.4"; \
else \
echo "Unsupported architecture: $TARGETARCH"; exit 1; \
fi; \
wget -nv https://github.com/mjun0812/flash-attention-prebuild-wheels/releases/download/${WHL_VERSION}/${WHL_FILE}; \
pip3 install --no-cache-dir ${WHL_FILE}; \
rm ${WHL_FILE}; \
fi \
;; \
esac