Merge remote-tracking branch 'refs/remotes/origin/main'

This commit is contained in:
oobabooga 2023-09-11 10:45:13 -07:00
commit 39f4800d94

View File

@ -1,15 +1,16 @@
FROM nvidia/cuda:11.8.0-devel-ubuntu22.04 as builder FROM nvidia/cuda:11.8.0-devel-ubuntu22.04 as builder
RUN apt-get update && \ 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 && \ apt-get install --no-install-recommends -y git vim build-essential python3-dev python3-venv && \
rm -rf /var/lib/apt/lists/* rm -rf /var/lib/apt/lists/*
RUN git clone https://github.com/oobabooga/GPTQ-for-LLaMa /build RUN git clone --depth=1 https://github.com/oobabooga/GPTQ-for-LLaMa /build
WORKDIR /build WORKDIR /build
RUN python3 -m venv /build/venv RUN --mount=type=cache,target=/root/.cache/pip,rw \
RUN . /build/venv/bin/activate && \ python3 -m venv /build/venv && \
. /build/venv/bin/activate && \
pip3 install --upgrade pip setuptools wheel && \ pip3 install --upgrade pip setuptools wheel && \
pip3 install torch torchvision torchaudio && \ pip3 install torch torchvision torchaudio && \
pip3 install -r requirements.txt pip3 install -r requirements.txt
@ -25,11 +26,11 @@ FROM nvidia/cuda:11.8.0-runtime-ubuntu22.04
LABEL maintainer="Your Name <your.email@example.com>" LABEL maintainer="Your Name <your.email@example.com>"
LABEL description="Docker image for GPTQ-for-LLaMa and Text Generation WebUI" LABEL description="Docker image for GPTQ-for-LLaMa and Text Generation WebUI"
RUN apt-get update && \ 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 && \ 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/* rm -rf /var/lib/apt/lists/*
RUN --mount=type=cache,target=/root/.cache/pip pip3 install virtualenv RUN --mount=type=cache,target=/root/.cache/pip,rw pip3 install virtualenv
RUN mkdir /app RUN mkdir /app
WORKDIR /app WORKDIR /app
@ -37,36 +38,38 @@ WORKDIR /app
ARG WEBUI_VERSION ARG WEBUI_VERSION
RUN test -n "${WEBUI_VERSION}" && git reset --hard ${WEBUI_VERSION} || echo "Using provided webui source" RUN test -n "${WEBUI_VERSION}" && git reset --hard ${WEBUI_VERSION} || echo "Using provided webui source"
# Create virtualenv
RUN virtualenv /app/venv RUN virtualenv /app/venv
RUN . /app/venv/bin/activate && \ RUN --mount=type=cache,target=/root/.cache/pip,rw \
. /app/venv/bin/activate && \
pip3 install --upgrade pip setuptools wheel && \ pip3 install --upgrade pip setuptools wheel && \
pip3 install torch torchvision torchaudio pip3 install torch torchvision torchaudio sentence_transformers xformers
# Copy and install GPTQ-for-LLaMa
COPY --from=builder /build /app/repositories/GPTQ-for-LLaMa COPY --from=builder /build /app/repositories/GPTQ-for-LLaMa
RUN . /app/venv/bin/activate && \ RUN --mount=type=cache,target=/root/.cache/pip,rw \
. /app/venv/bin/activate && \
pip3 install /app/repositories/GPTQ-for-LLaMa/*.whl pip3 install /app/repositories/GPTQ-for-LLaMa/*.whl
COPY extensions/api/requirements.txt /app/extensions/api/requirements.txt # Install main requirements
COPY extensions/elevenlabs_tts/requirements.txt /app/extensions/elevenlabs_tts/requirements.txt
COPY extensions/google_translate/requirements.txt /app/extensions/google_translate/requirements.txt
COPY extensions/silero_tts/requirements.txt /app/extensions/silero_tts/requirements.txt
COPY extensions/whisper_stt/requirements.txt /app/extensions/whisper_stt/requirements.txt
COPY extensions/superbooga/requirements.txt /app/extensions/superbooga/requirements.txt
COPY extensions/openai/requirements.txt /app/extensions/openai/requirements.txt
RUN --mount=type=cache,target=/root/.cache/pip . /app/venv/bin/activate && cd extensions/api && pip3 install -r requirements.txt
RUN --mount=type=cache,target=/root/.cache/pip . /app/venv/bin/activate && cd extensions/elevenlabs_tts && pip3 install -r requirements.txt
RUN --mount=type=cache,target=/root/.cache/pip . /app/venv/bin/activate && cd extensions/google_translate && pip3 install -r requirements.txt
RUN --mount=type=cache,target=/root/.cache/pip . /app/venv/bin/activate && cd extensions/silero_tts && pip3 install -r requirements.txt
RUN --mount=type=cache,target=/root/.cache/pip . /app/venv/bin/activate && cd extensions/whisper_stt && pip3 install -r requirements.txt
RUN --mount=type=cache,target=/root/.cache/pip . /app/venv/bin/activate && cd extensions/superbooga && pip3 install -r requirements.txt
RUN --mount=type=cache,target=/root/.cache/pip . /app/venv/bin/activate && cd extensions/openai && pip3 install -r requirements.txt
COPY requirements.txt /app/requirements.txt COPY requirements.txt /app/requirements.txt
RUN . /app/venv/bin/activate && \ RUN --mount=type=cache,target=/root/.cache/pip,rw \
. /app/venv/bin/activate && \
pip3 install -r requirements.txt 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 RUN cp /app/venv/lib/python3.10/site-packages/bitsandbytes/libbitsandbytes_cuda118.so /app/venv/lib/python3.10/site-packages/bitsandbytes/libbitsandbytes_cpu.so
COPY . /app/ # 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="" 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} CMD . /app/venv/bin/activate && python3 server.py ${CLI_ARGS}