Spaces:
Sleeping
Sleeping
File size: 2,842 Bytes
5354d0a |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 |
FROM nvidia/cuda:11.8.0-devel-ubuntu22.04 as builder
RUN --mount=type=cache,target=/var/cache/apt,sharing=locked,rw apt-get update && \
apt-get install --no-install-recommends -y git vim build-essential python3-dev python3-venv && \
rm -rf /var/lib/apt/lists/*
RUN git clone --depth=1 https://github.com/oobabooga/GPTQ-for-LLaMa /build
WORKDIR /build
RUN --mount=type=cache,target=/root/.cache/pip,rw \
python3 -m venv /build/venv && \
. /build/venv/bin/activate && \
pip3 install --upgrade pip setuptools wheel && \
pip3 install torch torchvision torchaudio && \
pip3 install -r requirements.txt
# https://developer.nvidia.com/cuda-gpus
# for a rtx 2060: ARG TORCH_CUDA_ARCH_LIST="7.5"
ARG TORCH_CUDA_ARCH_LIST="${TORCH_CUDA_ARCH_LIST:-3.5;5.0;6.0;6.1;7.0;7.5;8.0;8.6+PTX}"
RUN . /build/venv/bin/activate && \
python3 setup_cuda.py bdist_wheel -d .
FROM nvidia/cuda:11.8.0-runtime-ubuntu22.04
LABEL maintainer="Your Name <[email protected]>"
LABEL description="Docker image for GPTQ-for-LLaMa and Text Generation WebUI"
RUN --mount=type=cache,target=/var/cache/apt,sharing=locked,rw apt-get update && \
apt-get install --no-install-recommends -y python3-dev libportaudio2 libasound-dev git python3 python3-pip make g++ ffmpeg && \
rm -rf /var/lib/apt/lists/*
RUN --mount=type=cache,target=/root/.cache/pip,rw pip3 install virtualenv
RUN mkdir /app
WORKDIR /app
ARG WEBUI_VERSION
RUN test -n "${WEBUI_VERSION}" && git reset --hard ${WEBUI_VERSION} || echo "Using provided webui source"
# Create virtualenv
RUN virtualenv /app/venv
RUN --mount=type=cache,target=/root/.cache/pip,rw \
. /app/venv/bin/activate && \
pip3 install --upgrade pip setuptools wheel && \
pip3 install torch torchvision torchaudio sentence_transformers xformers
# Copy and install GPTQ-for-LLaMa
COPY --from=builder /build /app/repositories/GPTQ-for-LLaMa
RUN --mount=type=cache,target=/root/.cache/pip,rw \
. /app/venv/bin/activate && \
pip3 install /app/repositories/GPTQ-for-LLaMa/*.whl
# Install main requirements
COPY requirements.txt /app/requirements.txt
RUN --mount=type=cache,target=/root/.cache/pip,rw \
. /app/venv/bin/activate && \
pip3 install -r requirements.txt
COPY . /app/
RUN cp /app/venv/lib/python3.10/site-packages/bitsandbytes/libbitsandbytes_cuda118.so /app/venv/lib/python3.10/site-packages/bitsandbytes/libbitsandbytes_cpu.so
# Install extension requirements
RUN --mount=type=cache,target=/root/.cache/pip,rw \
. /app/venv/bin/activate && \
for ext in /app/extensions/*/requirements.txt; do \
cd "$(dirname "$ext")"; \
pip3 install -r requirements.txt; \
done
ENV CLI_ARGS=""
EXPOSE ${CONTAINER_PORT:-7860} ${CONTAINER_API_PORT:-5000} ${CONTAINER_API_STREAM_PORT:-5005}
CMD . /app/venv/bin/activate && python3 server.py ${CLI_ARGS}
|