vbatts/llama.cpp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

update CPU dockerfiles

Browse source
This commit is contained in:
slaren 2024-12-04 01:10:37 +01:00
parent 674dec9b36
commit 478194b1b6
3 changed files with 41 additions and 23 deletions
Download patch file Download diff file Expand all files Collapse all files

33
.devops/full.Dockerfile
View file

@ -3,23 +3,36 @@ ARG UBUNTU_VERSION=22.04
FROM ubuntu:$UBUNTU_VERSION AS build FROM ubuntu:$UBUNTU_VERSION AS build
RUN apt-get update && \ RUN apt-get update && \
apt-get install -y build-essential python3 python3-pip git libcurl4-openssl-dev libgomp1 apt-get install -y build-essential git cmake libcurl4-openssl-dev
COPY requirements.txt requirements.txt
COPY requirements requirements
RUN pip install --upgrade pip setuptools wheel \
&& pip install -r requirements.txt
WORKDIR /app WORKDIR /app
COPY . . COPY . .
ENV LLAMA_CURL=1 RUN cmake -S . -B build -DGGML_BACKEND_DL=ON -DGGML_NATIVE=OFF -DGGML_CPU_ALL_VARIANTS=ON -DLLAMA_CURL=ON -DCMAKE_BUILD_TYPE=Release && \
cmake --build build -j $(nproc) && \
mkdir -p /app/lib && \
find build -name "*.so" -exec cp {} /app/lib/ \;
FROM ubuntu:$UBUNTU_VERSION as runtime
RUN make -j$(nproc) WORKDIR /app
RUN apt-get update && \
apt-get install -y build-essential python3 python3-pip git libcurl4-openssl-dev libgomp1
COPY requirements.txt /app/requirements.txt
COPY requirements /app/requirements
COPY .devops/tools.sh /app/tools.sh
RUN pip install --upgrade pip setuptools wheel && \
pip install -r /app/requirements.txt
COPY --from=build /app/build/bin/ /app/
COPY --from=build /app/lib/ /app/
COPY --from=build /app/convert_hf_to_gguf.py /app/
COPY --from=build /app/gguf-py /app/gguf-py
ENV LC_ALL=C.utf8 ENV LC_ALL=C.utf8
ENTRYPOINT ["/app/.devops/tools.sh"] ENTRYPOINT ["/app/tools.sh"]

18
.devops/llama-cli.Dockerfile
View file

@ -3,21 +3,27 @@ ARG UBUNTU_VERSION=22.04
FROM ubuntu:$UBUNTU_VERSION AS build FROM ubuntu:$UBUNTU_VERSION AS build
RUN apt-get update && \ RUN apt-get update && \
apt-get install -y build-essential git apt-get install -y build-essential git cmake libcurl4-openssl-dev
WORKDIR /app WORKDIR /app
COPY . . COPY . .
RUN make -j$(nproc) llama-cli RUN cmake -S . -B build -DGGML_BACKEND_DL=ON -DGGML_NATIVE=OFF -DGGML_CPU_ALL_VARIANTS=ON -DLLAMA_CURL=ON -DCMAKE_BUILD_TYPE=Release && \
cmake --build build -j $(nproc) && \
mkdir -p /app/lib && \
find build -name "*.so" -exec cp {} /app/lib/ \;
FROM ubuntu:$UBUNTU_VERSION AS runtime FROM ubuntu:$UBUNTU_VERSION AS runtime
RUN apt-get update && \ WORKDIR /app
apt-get install -y libgomp1
COPY --from=build /app/llama-cli /llama-cli RUN apt-get update && \
apt-get install -y libcurl4-openssl-dev libgomp1 curl
COPY --from=build /app/build/bin/llama-cli /app/
COPY --from=build /app/lib/ /app/
ENV LC_ALL=C.utf8 ENV LC_ALL=C.utf8
ENTRYPOINT [ "/llama-cli" ] ENTRYPOINT [ "/app/llama-cli" ]

13
.devops/llama-server.Dockerfile
View file

@ -9,21 +9,20 @@ WORKDIR /app
COPY . . COPY . .
RUN \ RUN cmake -S . -B build -DGGML_BACKEND_DL=ON -DGGML_NATIVE=OFF -DGGML_CPU_ALL_VARIANTS=ON -DLLAMA_CURL=ON -DCMAKE_BUILD_TYPE=Release && \
# Build llama-server
cmake -S . -B build -DGGML_BACKEND_DL=ON -DGGML_NATIVE=OFF -DGGML_CPU_ALL_VARIANTS=ON -DLLAMA_CURL=ON -DCMAKE_BUILD_TYPE=Release && \
cmake --build build -j $(nproc) && \ cmake --build build -j $(nproc) && \
# Copy the built libraries to /app/lib
mkdir -p /app/lib && \ mkdir -p /app/lib && \
find build -name "*.so" -exec cp {} /app/lib/ \; find build -name "*.so" -exec cp {} /app/lib/ \;
FROM ubuntu:$UBUNTU_VERSION AS runtime FROM ubuntu:$UBUNTU_VERSION AS runtime
WORKDIR /app
RUN apt-get update && \ RUN apt-get update && \
apt-get install -y libcurl4-openssl-dev libgomp1 curl apt-get install -y libcurl4-openssl-dev libgomp1 curl
COPY --from=build /app/build/bin/llama-server /llama-server COPY --from=build /app/build/bin/llama-server /app/
COPY --from=build /app/lib/ / COPY --from=build /app/lib/ /app/
ENV LC_ALL=C.utf8 ENV LC_ALL=C.utf8
# Must be set to 0.0.0.0 so it can listen to requests from host machine # Must be set to 0.0.0.0 so it can listen to requests from host machine
@ -31,4 +30,4 @@ ENV LLAMA_ARG_HOST=0.0.0.0
HEALTHCHECK CMD [ "curl", "-f", "http://localhost:8080/health" ] HEALTHCHECK CMD [ "curl", "-f", "http://localhost:8080/health" ]
ENTRYPOINT [ "/llama-server" ] ENTRYPOINT [ "/app/llama-server" ]