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

ggml : add predefined list of CPU backend variants to build (#10626)

Browse source 
* ggml : add predefined list of CPU backend variants to build

* update CPU dockerfiles
This commit is contained in:
Diego Devesa 2024-12-04 14:45:40 +01:00 • committed by GitHub
parent 2803540814
commit 59f4db1088
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
11 changed files with 502 additions and 391 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
RUN apt-get update && \
apt-get install -y build-essential python3 python3-pip git libcurl4-openssl-dev libgomp1
COPY requirements.txt requirements.txt
COPY requirements requirements
RUN pip install --upgrade pip setuptools wheel \
&& pip install -r requirements.txt
apt-get install -y build-essential git cmake libcurl4-openssl-dev
WORKDIR /app
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
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:$UBUNTU_VERSION AS build
RUN apt-get update && \
apt-get install -y build-essential git
apt-get install -y build-essential git cmake libcurl4-openssl-dev
WORKDIR /app
COPY . .
RUN make -j$(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
RUN apt-get update && \
apt-get install -y libgomp1
WORKDIR /app
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
ENTRYPOINT [ "/llama-cli" ]
ENTRYPOINT [ "/app/llama-cli" ]

22
.devops/llama-server.Dockerfile
View file

@ -9,28 +9,20 @@ WORKDIR /app
COPY . .
RUN \
# Build multiple versions of the CPU backend
scripts/build-cpu.sh avx -DGGML_AVX=ON -DGGML_AVX2=OFF && \
scripts/build-cpu.sh avx2 -DGGML_AVX=ON -DGGML_AVX2=ON && \
scripts/build-cpu.sh avx512 -DGGML_AVX=ON -DGGML_AVX2=ON -DGGML_AVX512=ON && \
scripts/build-cpu.sh amx -DGGML_AVX=ON -DGGML_AVX2=ON -DGGML_AVX512=ON -DGGML_AVX_VNNI=ON -DGGML_AVX512_VNNI=ON -DGGML_AMX_TILE=ON -DGGML_AMX_INT8=ON && \
# Build llama-server
cmake -S . -B build -DGGML_BACKEND_DL=ON -DGGML_NATIVE=OFF -DLLAMA_CURL=ON -DCMAKE_BUILD_TYPE=Release && \
cmake --build build --target llama-server -j $(nproc) && \
# Copy the built libraries to /app/lib
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 $(nproc) && \
mkdir -p /app/lib && \
mv libggml-cpu* /app/lib/ && \
find build -name "*.so" -exec cp {} /app/lib/ \;
FROM ubuntu:$UBUNTU_VERSION AS runtime
WORKDIR /app
RUN apt-get update && \
apt-get install -y libcurl4-openssl-dev libgomp1 curl
COPY --from=build /app/build/bin/llama-server /llama-server
COPY --from=build /app/lib/ /
COPY --from=build /app/build/bin/llama-server /app/
COPY --from=build /app/lib/ /app/
ENV LC_ALL=C.utf8
# Must be set to 0.0.0.0 so it can listen to requests from host machine
@ -38,4 +30,4 @@ ENV LLAMA_ARG_HOST=0.0.0.0
HEALTHCHECK CMD [ "curl", "-f", "http://localhost:8080/health" ]
ENTRYPOINT [ "/llama-server" ]
ENTRYPOINT [ "/app/llama-server" ]