81 lines
2.4 KiB
Docker
81 lines
2.4 KiB
Docker
FROM nvidia/cuda:11.2.2-cudnn8-devel-ubuntu20.04 as builder
|
|
|
|
RUN apt-get update && \
|
|
apt-get install -y --no-install-recommends \
|
|
python3-dev \
|
|
python3-pip \
|
|
wget \
|
|
pkg-config \
|
|
libssl-dev \
|
|
&& \
|
|
apt-get clean && \
|
|
rm -rf /var/lib/apt/lists/*
|
|
|
|
WORKDIR /root
|
|
|
|
ENV ONEAPI_VERSION=2023.0.0
|
|
ENV MKL_BUILD=25398
|
|
RUN wget -q https://apt.repos.intel.com/intel-gpg-keys/GPG-PUB-KEY-INTEL-SW-PRODUCTS.PUB && \
|
|
apt-key add *.PUB && \
|
|
rm *.PUB && \
|
|
echo "deb https://apt.repos.intel.com/oneapi all main" > /etc/apt/sources.list.d/oneAPI.list && \
|
|
apt-get update && \
|
|
apt-get install -y --no-install-recommends \
|
|
intel-oneapi-mkl-devel=$ONEAPI_VERSION-$MKL_BUILD \
|
|
&& \
|
|
apt-get clean && \
|
|
rm -rf /var/lib/apt/lists/*
|
|
|
|
RUN python3 -m pip --no-cache-dir install cmake==3.22.*
|
|
|
|
ENV ONEDNN_VERSION=3.0.1
|
|
RUN wget -q https://github.com/oneapi-src/oneDNN/archive/refs/tags/v${ONEDNN_VERSION}.tar.gz && \
|
|
tar xf *.tar.gz && \
|
|
rm *.tar.gz && \
|
|
cd oneDNN-* && \
|
|
cmake -DCMAKE_BUILD_TYPE=Release -DDNNL_LIBRARY_TYPE=STATIC -DDNNL_BUILD_EXAMPLES=OFF -DDNNL_BUILD_TESTS=OFF -DDNNL_ENABLE_WORKLOAD=INFERENCE -DDNNL_ENABLE_PRIMITIVE="CONVOLUTION;REORDER" . && \
|
|
make -j$(nproc) install && \
|
|
cd .. && \
|
|
rm -r oneDNN-*
|
|
|
|
|
|
# setup rust.
|
|
RUN wget -O - https://sh.rustup.rs | bash -s -- -y
|
|
ENV PATH="/root/.cargo/bin:${PATH}"
|
|
|
|
COPY crates crates
|
|
|
|
WORKDIR /root/crates/tabby
|
|
RUN mkdir -p target
|
|
RUN --mount=type=cache,target=/usr/local/cargo/registry \
|
|
--mount=type=cache,target=/root/crates/tabby/target \
|
|
cargo build --release
|
|
|
|
RUN mkdir -p /opt/tabby/bin
|
|
RUN cp target/release/tabby /opt/tabby/bin/
|
|
|
|
RUN mkdir -p /opt/tabby/lib
|
|
RUN cp $(dirname $(find target | grep lib/libctranslate2 | head -1))/libctranslate2* /opt/tabby/lib
|
|
|
|
FROM nvidia/cuda:11.2.2-base-ubuntu20.04
|
|
|
|
# We remove the cuda-compat package because it conflicts with the CUDA Enhanced Compatibility.
|
|
# See e.g. https://github.com/NVIDIA/nvidia-docker/issues/1515
|
|
RUN apt-get update && \
|
|
apt-get install -y --no-install-recommends \
|
|
libcublas-11-2 \
|
|
libcudnn8=8.1.1.33-1+cuda11.2 \
|
|
libgomp1 \
|
|
python3-pip \
|
|
&& \
|
|
apt-get purge -y cuda-compat-11-2 && \
|
|
apt-get clean && \
|
|
rm -rf /var/lib/apt/lists/*
|
|
|
|
ENV TABBY_ROOT=/opt/tabby
|
|
ENV LD_LIBRARY_PATH=$LD_LIBRARY_PATH:$TABBY_ROOT/lib
|
|
|
|
COPY --from=builder $TABBY_ROOT $TABBY_ROOT
|
|
|
|
ENTRYPOINT ["/opt/tabby/bin/tabby"]
|