mirror of
https://github.com/ggerganov/llama.cpp.git
synced 2024-12-24 10:24:35 +00:00
devops : add docker-multi-stage builds (#10832)
This commit is contained in:
Rudi Servo
GitHub
parent
7ae33a616f
commit
7c0e285858
81
.devops/cpu.Dockerfile
Normal file
81
.devops/cpu.Dockerfile
Normal file
@ -0,0 +1,81 @@
|
||||
ARG UBUNTU_VERSION=22.04
|
||||
|
||||
FROM ubuntu:$UBUNTU_VERSION AS build
|
||||
|
||||
RUN apt-get update && \
|
||||
apt-get install -y build-essential git cmake libcurl4-openssl-dev
|
||||
|
||||
WORKDIR /app
|
||||
|
||||
COPY . .
|
||||
|
||||
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 $(nproc)
|
||||
|
||||
RUN mkdir -p /app/lib && \
|
||||
find build -name "*.so" -exec cp {} /app/lib \;
|
||||
|
||||
RUN mkdir -p /app/full \
|
||||
&& cp build/bin/* /app/full \
|
||||
&& cp *.py /app/full \
|
||||
&& cp -r gguf-py /app/full \
|
||||
&& cp -r requirements /app/full \
|
||||
&& cp requirements.txt /app/full \
|
||||
&& cp .devops/tools.sh /app/full/tools.sh
|
||||
|
||||
## Base image
|
||||
FROM ubuntu:$UBUNTU_VERSION AS base
|
||||
|
||||
RUN apt-get update \
|
||||
&& apt-get install -y libgomp1 curl\
|
||||
&& apt autoremove -y \
|
||||
&& apt clean -y \
|
||||
&& rm -rf /tmp/* /var/tmp/* \
|
||||
&& find /var/cache/apt/archives /var/lib/apt/lists -not -name lock -type f -delete \
|
||||
&& find /var/cache -type f -delete
|
||||
|
||||
COPY --from=build /app/lib/ /app
|
||||
|
||||
### Full
|
||||
FROM base AS full
|
||||
|
||||
COPY --from=build /app/full /app
|
||||
|
||||
WORKDIR /app
|
||||
|
||||
RUN apt-get update \
|
||||
&& apt-get install -y \
|
||||
git \
|
||||
python3 \
|
||||
python3-pip \
|
||||
&& pip install --upgrade pip setuptools wheel \
|
||||
&& pip install -r requirements.txt \
|
||||
&& apt autoremove -y \
|
||||
&& apt clean -y \
|
||||
&& rm -rf /tmp/* /var/tmp/* \
|
||||
&& find /var/cache/apt/archives /var/lib/apt/lists -not -name lock -type f -delete \
|
||||
&& find /var/cache -type f -delete
|
||||
|
||||
ENTRYPOINT ["/app/tools.sh"]
|
||||
|
||||
### Light, CLI only
|
||||
FROM base AS light
|
||||
|
||||
COPY --from=build /app/full/llama-cli /app
|
||||
|
||||
WORKDIR /app
|
||||
|
||||
ENTRYPOINT [ "/app/llama-cli" ]
|
||||
|
||||
### Server, Server only
|
||||
FROM base AS server
|
||||
|
||||
ENV LLAMA_ARG_HOST=0.0.0.0
|
||||
|
||||
COPY --from=build /app/full/llama-server /app
|
||||
|
||||
WORKDIR /app
|
||||
|
||||
HEALTHCHECK CMD [ "curl", "-f", "http://localhost:8080/health" ]
|
||||
|
||||
ENTRYPOINT [ "/app/llama-server" ]
|
||||
94
.devops/cuda.Dockerfile
Normal file
94
.devops/cuda.Dockerfile
Normal file
@ -0,0 +1,94 @@
|
||||
ARG UBUNTU_VERSION=22.04
|
||||
# This needs to generally match the container host's environment.
|
||||
ARG CUDA_VERSION=12.6.0
|
||||
# Target the CUDA build image
|
||||
ARG BASE_CUDA_DEV_CONTAINER=nvidia/cuda:${CUDA_VERSION}-devel-ubuntu${UBUNTU_VERSION}
|
||||
|
||||
ARG BASE_CUDA_RUN_CONTAINER=nvidia/cuda:${CUDA_VERSION}-runtime-ubuntu${UBUNTU_VERSION}
|
||||
|
||||
FROM ${BASE_CUDA_DEV_CONTAINER} AS build
|
||||
|
||||
# CUDA architecture to build for (defaults to all supported archs)
|
||||
ARG CUDA_DOCKER_ARCH=default
|
||||
|
||||
RUN apt-get update && \
|
||||
apt-get install -y build-essential cmake python3 python3-pip git libcurl4-openssl-dev libgomp1
|
||||
|
||||
WORKDIR /app
|
||||
|
||||
COPY . .
|
||||
|
||||
RUN if [ "${CUDA_DOCKER_ARCH}" != "default" ]; then \
|
||||
export CMAKE_ARGS="-DCMAKE_CUDA_ARCHITECTURES=${CUDA_DOCKER_ARCH}"; \
|
||||
fi && \
|
||||
cmake -B build -DGGML_NATIVE=OFF -DGGML_CUDA=ON -DLLAMA_CURL=ON ${CMAKE_ARGS} -DCMAKE_EXE_LINKER_FLAGS=-Wl,--allow-shlib-undefined . && \
|
||||
cmake --build build --config Release -j$(nproc)
|
||||
|
||||
RUN mkdir -p /app/lib && \
|
||||
find build -name "*.so" -exec cp {} /app/lib \;
|
||||
|
||||
RUN mkdir -p /app/full \
|
||||
&& cp build/bin/* /app/full \
|
||||
&& cp *.py /app/full \
|
||||
&& cp -r gguf-py /app/full \
|
||||
&& cp -r requirements /app/full \
|
||||
&& cp requirements.txt /app/full \
|
||||
&& cp .devops/tools.sh /app/full/tools.sh
|
||||
|
||||
## Base image
|
||||
FROM ${BASE_CUDA_RUN_CONTAINER} AS base
|
||||
|
||||
RUN apt-get update \
|
||||
&& apt-get install -y libgomp1 curl\
|
||||
&& apt autoremove -y \
|
||||
&& apt clean -y \
|
||||
&& rm -rf /tmp/* /var/tmp/* \
|
||||
&& find /var/cache/apt/archives /var/lib/apt/lists -not -name lock -type f -delete \
|
||||
&& find /var/cache -type f -delete
|
||||
|
||||
COPY --from=build /app/lib/ /app
|
||||
|
||||
### Full
|
||||
FROM base AS full
|
||||
|
||||
COPY --from=build /app/full /app
|
||||
|
||||
WORKDIR /app
|
||||
|
||||
RUN apt-get update \
|
||||
&& apt-get install -y \
|
||||
git \
|
||||
python3 \
|
||||
python3-pip \
|
||||
&& pip install --upgrade pip setuptools wheel \
|
||||
&& pip install -r requirements.txt \
|
||||
&& apt autoremove -y \
|
||||
&& apt clean -y \
|
||||
&& rm -rf /tmp/* /var/tmp/* \
|
||||
&& find /var/cache/apt/archives /var/lib/apt/lists -not -name lock -type f -delete \
|
||||
&& find /var/cache -type f -delete
|
||||
|
||||
|
||||
ENTRYPOINT ["/app/tools.sh"]
|
||||
|
||||
### Light, CLI only
|
||||
FROM base AS light
|
||||
|
||||
COPY --from=build /app/full/llama-cli /app
|
||||
|
||||
WORKDIR /app
|
||||
|
||||
ENTRYPOINT [ "/app/llama-cli" ]
|
||||
|
||||
### Server, Server only
|
||||
FROM base AS server
|
||||
|
||||
ENV LLAMA_ARG_HOST=0.0.0.0
|
||||
|
||||
COPY --from=build /app/full/llama-server /app
|
||||
|
||||
WORKDIR /app
|
||||
|
||||
HEALTHCHECK CMD [ "curl", "-f", "http://localhost:8080/health" ]
|
||||
|
||||
ENTRYPOINT [ "/app/llama-server" ]
|
||||
@ -1,33 +0,0 @@
|
||||
ARG UBUNTU_VERSION=22.04
|
||||
# This needs to generally match the container host's environment.
|
||||
ARG CUDA_VERSION=12.6.0
|
||||
# Target the CUDA build image
|
||||
ARG BASE_CUDA_DEV_CONTAINER=nvidia/cuda:${CUDA_VERSION}-devel-ubuntu${UBUNTU_VERSION}
|
||||
|
||||
FROM ${BASE_CUDA_DEV_CONTAINER} AS build
|
||||
|
||||
# CUDA architecture to build for (defaults to all supported archs)
|
||||
ARG CUDA_DOCKER_ARCH=default
|
||||
|
||||
RUN apt-get update && \
|
||||
apt-get install -y build-essential cmake python3 python3-pip git libcurl4-openssl-dev libgomp1
|
||||
|
||||
COPY requirements.txt requirements.txt
|
||||
COPY requirements requirements
|
||||
|
||||
RUN pip install --upgrade pip setuptools wheel \
|
||||
&& pip install -r requirements.txt
|
||||
|
||||
WORKDIR /app
|
||||
|
||||
COPY . .
|
||||
|
||||
# Use the default CUDA archs if not specified
|
||||
RUN if [ "${CUDA_DOCKER_ARCH}" != "default" ]; then \
|
||||
export CMAKE_ARGS="-DCMAKE_CUDA_ARCHITECTURES=${CUDA_DOCKER_ARCH}"; \
|
||||
fi && \
|
||||
cmake -B build -DGGML_NATIVE=OFF -DGGML_CUDA=ON -DLLAMA_CURL=ON ${CMAKE_ARGS} -DCMAKE_EXE_LINKER_FLAGS=-Wl,--allow-shlib-undefined . && \
|
||||
cmake --build build --config Release -j$(nproc) && \
|
||||
cp build/bin/* .
|
||||
|
||||
ENTRYPOINT ["/app/.devops/tools.sh"]
|
||||
@ -1,33 +0,0 @@
|
||||
ARG UBUNTU_VERSION=22.04
|
||||
# This needs to generally match the container host's environment.
|
||||
ARG MUSA_VERSION=rc3.1.0
|
||||
# Target the MUSA build image
|
||||
ARG BASE_MUSA_DEV_CONTAINER=mthreads/musa:${MUSA_VERSION}-devel-ubuntu${UBUNTU_VERSION}
|
||||
|
||||
FROM ${BASE_MUSA_DEV_CONTAINER} AS build
|
||||
|
||||
# MUSA architecture to build for (defaults to all supported archs)
|
||||
ARG MUSA_DOCKER_ARCH=default
|
||||
|
||||
RUN apt-get update && \
|
||||
apt-get install -y build-essential cmake python3 python3-pip git libcurl4-openssl-dev libgomp1
|
||||
|
||||
COPY requirements.txt requirements.txt
|
||||
COPY requirements requirements
|
||||
|
||||
RUN pip install --upgrade pip setuptools wheel \
|
||||
&& pip install -r requirements.txt
|
||||
|
||||
WORKDIR /app
|
||||
|
||||
COPY . .
|
||||
|
||||
# Use the default MUSA archs if not specified
|
||||
RUN if [ "${MUSA_DOCKER_ARCH}" != "default" ]; then \
|
||||
export CMAKE_ARGS="-DMUSA_ARCHITECTURES=${MUSA_DOCKER_ARCH}"; \
|
||||
fi && \
|
||||
cmake -B build -DGGML_NATIVE=OFF -DGGML_MUSA=ON -DLLAMA_CURL=ON ${CMAKE_ARGS} -DCMAKE_EXE_LINKER_FLAGS=-Wl,--allow-shlib-undefined . && \
|
||||
cmake --build build --config Release -j$(nproc) && \
|
||||
cp build/bin/* .
|
||||
|
||||
ENTRYPOINT ["/app/.devops/tools.sh"]
|
||||
@ -1,50 +0,0 @@
|
||||
ARG UBUNTU_VERSION=22.04
|
||||
|
||||
# This needs to generally match the container host's environment.
|
||||
ARG ROCM_VERSION=5.6
|
||||
|
||||
# Target the CUDA build image
|
||||
ARG BASE_ROCM_DEV_CONTAINER=rocm/dev-ubuntu-${UBUNTU_VERSION}:${ROCM_VERSION}-complete
|
||||
|
||||
FROM ${BASE_ROCM_DEV_CONTAINER} AS build
|
||||
|
||||
# Unless otherwise specified, we make a fat build.
|
||||
# List from https://github.com/ggerganov/llama.cpp/pull/1087#issuecomment-1682807878
|
||||
# This is mostly tied to rocBLAS supported archs.
|
||||
ARG ROCM_DOCKER_ARCH="\
|
||||
gfx803 \
|
||||
gfx900 \
|
||||
gfx906 \
|
||||
gfx908 \
|
||||
gfx90a \
|
||||
gfx1010 \
|
||||
gfx1030 \
|
||||
gfx1100 \
|
||||
gfx1101 \
|
||||
gfx1102"
|
||||
|
||||
COPY requirements.txt requirements.txt
|
||||
COPY requirements requirements
|
||||
|
||||
RUN pip install --upgrade pip setuptools wheel \
|
||||
&& pip install -r requirements.txt
|
||||
|
||||
WORKDIR /app
|
||||
|
||||
COPY . .
|
||||
|
||||
# Set nvcc architecture
|
||||
ENV AMDGPU_TARGETS=${ROCM_DOCKER_ARCH}
|
||||
# Enable ROCm
|
||||
ENV GGML_HIPBLAS=1
|
||||
ENV CC=/opt/rocm/llvm/bin/clang
|
||||
ENV CXX=/opt/rocm/llvm/bin/clang++
|
||||
|
||||
# Enable cURL
|
||||
ENV LLAMA_CURL=1
|
||||
RUN apt-get update && \
|
||||
apt-get install -y libcurl4-openssl-dev
|
||||
|
||||
RUN make -j$(nproc)
|
||||
|
||||
ENTRYPOINT ["/app/.devops/tools.sh"]
|
||||
@ -1,38 +0,0 @@
|
||||
ARG UBUNTU_VERSION=22.04
|
||||
|
||||
FROM ubuntu:$UBUNTU_VERSION AS build
|
||||
|
||||
RUN apt-get update && \
|
||||
apt-get install -y build-essential git cmake libcurl4-openssl-dev
|
||||
|
||||
WORKDIR /app
|
||||
|
||||
COPY . .
|
||||
|
||||
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
|
||||
|
||||
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/tools.sh"]
|
||||
91
.devops/intel.Dockerfile
Normal file
91
.devops/intel.Dockerfile
Normal file
@ -0,0 +1,91 @@
|
||||
ARG ONEAPI_VERSION=2025.0.0-0-devel-ubuntu22.04
|
||||
|
||||
## Build Image
|
||||
|
||||
FROM intel/oneapi-basekit:$ONEAPI_VERSION AS build
|
||||
|
||||
ARG GGML_SYCL_F16=OFF
|
||||
RUN apt-get update && \
|
||||
apt-get install -y git libcurl4-openssl-dev
|
||||
|
||||
WORKDIR /app
|
||||
|
||||
COPY . .
|
||||
|
||||
RUN if [ "${GGML_SYCL_F16}" = "ON" ]; then \
|
||||
echo "GGML_SYCL_F16 is set" \
|
||||
&& export OPT_SYCL_F16="-DGGML_SYCL_F16=ON"; \
|
||||
fi && \
|
||||
echo "Building with dynamic libs" && \
|
||||
cmake -B build -DGGML_NATIVE=OFF -DGGML_SYCL=ON -DCMAKE_C_COMPILER=icx -DCMAKE_CXX_COMPILER=icpx -DLLAMA_CURL=ON ${OPT_SYCL_F16} && \
|
||||
cmake --build build --config Release -j$(nproc)
|
||||
|
||||
RUN mkdir -p /app/lib && \
|
||||
find build -name "*.so" -exec cp {} /app/lib \;
|
||||
|
||||
RUN mkdir -p /app/full \
|
||||
&& cp build/bin/* /app/full \
|
||||
&& cp *.py /app/full \
|
||||
&& cp -r gguf-py /app/full \
|
||||
&& cp -r requirements /app/full \
|
||||
&& cp requirements.txt /app/full \
|
||||
&& cp .devops/tools.sh /app/full/tools.sh
|
||||
|
||||
FROM intel/oneapi-basekit:$ONEAPI_VERSION AS base
|
||||
|
||||
RUN apt-get update \
|
||||
&& apt-get install -y libgomp1 curl\
|
||||
&& apt autoremove -y \
|
||||
&& apt clean -y \
|
||||
&& rm -rf /tmp/* /var/tmp/* \
|
||||
&& find /var/cache/apt/archives /var/lib/apt/lists -not -name lock -type f -delete \
|
||||
&& find /var/cache -type f -delete
|
||||
|
||||
### Full
|
||||
FROM base AS full
|
||||
|
||||
COPY --from=build /app/lib/ /app
|
||||
COPY --from=build /app/full /app
|
||||
|
||||
WORKDIR /app
|
||||
|
||||
RUN apt-get update \
|
||||
&& apt-get install -y \
|
||||
git \
|
||||
python3 \
|
||||
python3-pip \
|
||||
&& pip install --upgrade pip setuptools wheel \
|
||||
&& pip install -r requirements.txt \
|
||||
&& apt autoremove -y \
|
||||
&& apt clean -y \
|
||||
&& rm -rf /tmp/* /var/tmp/* \
|
||||
&& find /var/cache/apt/archives /var/lib/apt/lists -not -name lock -type f -delete \
|
||||
&& find /var/cache -type f -delete
|
||||
|
||||
|
||||
ENTRYPOINT ["/app/tools.sh"]
|
||||
|
||||
### Light, CLI only
|
||||
FROM base AS light
|
||||
|
||||
COPY --from=build /app/lib/ /app
|
||||
COPY --from=build /app/full/llama-cli /app
|
||||
|
||||
WORKDIR /app
|
||||
|
||||
ENTRYPOINT [ "/app/llama-cli" ]
|
||||
|
||||
### Server, Server only
|
||||
FROM base AS server
|
||||
|
||||
ENV LLAMA_ARG_HOST=0.0.0.0
|
||||
|
||||
COPY --from=build /app/lib/ /app
|
||||
COPY --from=build /app/full/llama-server /app
|
||||
|
||||
WORKDIR /app
|
||||
|
||||
HEALTHCHECK CMD [ "curl", "-f", "http://localhost:8080/health" ]
|
||||
|
||||
ENTRYPOINT [ "/app/llama-server" ]
|
||||
|
||||
@ -1,38 +0,0 @@
|
||||
ARG UBUNTU_VERSION=22.04
|
||||
# This needs to generally match the container host's environment.
|
||||
ARG CUDA_VERSION=12.6.0
|
||||
# Target the CUDA build image
|
||||
ARG BASE_CUDA_DEV_CONTAINER=nvidia/cuda:${CUDA_VERSION}-devel-ubuntu${UBUNTU_VERSION}
|
||||
# Target the CUDA runtime image
|
||||
ARG BASE_CUDA_RUN_CONTAINER=nvidia/cuda:${CUDA_VERSION}-runtime-ubuntu${UBUNTU_VERSION}
|
||||
|
||||
FROM ${BASE_CUDA_DEV_CONTAINER} AS build
|
||||
|
||||
# CUDA architecture to build for (defaults to all supported archs)
|
||||
ARG CUDA_DOCKER_ARCH=default
|
||||
|
||||
RUN apt-get update && \
|
||||
apt-get install -y build-essential git cmake
|
||||
|
||||
WORKDIR /app
|
||||
|
||||
COPY . .
|
||||
|
||||
# Use the default CUDA archs if not specified
|
||||
RUN if [ "${CUDA_DOCKER_ARCH}" != "default" ]; then \
|
||||
export CMAKE_ARGS="-DCMAKE_CUDA_ARCHITECTURES=${CUDA_DOCKER_ARCH}"; \
|
||||
fi && \
|
||||
cmake -B build -DGGML_NATIVE=OFF -DGGML_CUDA=ON ${CMAKE_ARGS} -DCMAKE_EXE_LINKER_FLAGS=-Wl,--allow-shlib-undefined . && \
|
||||
cmake --build build --config Release --target llama-cli -j$(nproc) && \
|
||||
mkdir -p /app/lib && \
|
||||
find build -name "*.so" -exec cp {} /app/lib \;
|
||||
|
||||
FROM ${BASE_CUDA_RUN_CONTAINER} AS runtime
|
||||
|
||||
RUN apt-get update && \
|
||||
apt-get install -y libgomp1
|
||||
|
||||
COPY --from=build /app/lib/ /
|
||||
COPY --from=build /app/build/bin/llama-cli /
|
||||
|
||||
ENTRYPOINT [ "/llama-cli" ]
|
||||
@ -1,28 +0,0 @@
|
||||
ARG ONEAPI_VERSION=2025.0.0-0-devel-ubuntu22.04
|
||||
|
||||
FROM intel/oneapi-basekit:$ONEAPI_VERSION AS build
|
||||
|
||||
ARG GGML_SYCL_F16=OFF
|
||||
RUN apt-get update && \
|
||||
apt-get install -y git
|
||||
|
||||
WORKDIR /app
|
||||
|
||||
COPY . .
|
||||
|
||||
RUN if [ "${GGML_SYCL_F16}" = "ON" ]; then \
|
||||
echo "GGML_SYCL_F16 is set" && \
|
||||
export OPT_SYCL_F16="-DGGML_SYCL_F16=ON"; \
|
||||
fi && \
|
||||
echo "Building with static libs" && \
|
||||
cmake -B build -DGGML_NATIVE=OFF -DGGML_SYCL=ON -DCMAKE_C_COMPILER=icx -DCMAKE_CXX_COMPILER=icpx \
|
||||
${OPT_SYCL_F16} -DBUILD_SHARED_LIBS=OFF && \
|
||||
cmake --build build --config Release --target llama-cli
|
||||
|
||||
FROM intel/oneapi-basekit:$ONEAPI_VERSION AS runtime
|
||||
|
||||
COPY --from=build /app/build/bin/llama-cli /llama-cli
|
||||
|
||||
ENV LC_ALL=C.utf8
|
||||
|
||||
ENTRYPOINT [ "/llama-cli" ]
|
||||
@ -1,38 +0,0 @@
|
||||
ARG UBUNTU_VERSION=22.04
|
||||
# This needs to generally match the container host's environment.
|
||||
ARG MUSA_VERSION=rc3.1.0
|
||||
# Target the MUSA build image
|
||||
ARG BASE_MUSA_DEV_CONTAINER=mthreads/musa:${MUSA_VERSION}-devel-ubuntu${UBUNTU_VERSION}
|
||||
# Target the MUSA runtime image
|
||||
ARG BASE_MUSA_RUN_CONTAINER=mthreads/musa:${MUSA_VERSION}-runtime-ubuntu${UBUNTU_VERSION}
|
||||
|
||||
FROM ${BASE_MUSA_DEV_CONTAINER} AS build
|
||||
|
||||
# MUSA architecture to build for (defaults to all supported archs)
|
||||
ARG MUSA_DOCKER_ARCH=default
|
||||
|
||||
RUN apt-get update && \
|
||||
apt-get install -y build-essential git cmake
|
||||
|
||||
WORKDIR /app
|
||||
|
||||
COPY . .
|
||||
|
||||
# Use the default MUSA archs if not specified
|
||||
RUN if [ "${MUSA_DOCKER_ARCH}" != "default" ]; then \
|
||||
export CMAKE_ARGS="-DMUSA_ARCHITECTURES=${MUSA_DOCKER_ARCH}"; \
|
||||
fi && \
|
||||
cmake -B build -DGGML_NATIVE=OFF -DGGML_MUSA=ON ${CMAKE_ARGS} -DCMAKE_EXE_LINKER_FLAGS=-Wl,--allow-shlib-undefined . && \
|
||||
cmake --build build --config Release --target llama-cli -j$(nproc) && \
|
||||
mkdir -p /app/lib && \
|
||||
find build -name "*.so" -exec cp {} /app/lib \;
|
||||
|
||||
FROM ${BASE_MUSA_RUN_CONTAINER} AS runtime
|
||||
|
||||
RUN apt-get update && \
|
||||
apt-get install -y libgomp1
|
||||
|
||||
COPY --from=build /app/lib/ /
|
||||
COPY --from=build /app/build/bin/llama-cli /llama-cli
|
||||
|
||||
ENTRYPOINT [ "/llama-cli" ]
|
||||
@ -1,45 +0,0 @@
|
||||
ARG UBUNTU_VERSION=22.04
|
||||
|
||||
# This needs to generally match the container host's environment.
|
||||
ARG ROCM_VERSION=5.6
|
||||
|
||||
# Target the CUDA build image
|
||||
ARG BASE_ROCM_DEV_CONTAINER=rocm/dev-ubuntu-${UBUNTU_VERSION}:${ROCM_VERSION}-complete
|
||||
|
||||
FROM ${BASE_ROCM_DEV_CONTAINER} AS build
|
||||
|
||||
# Unless otherwise specified, we make a fat build.
|
||||
# List from https://github.com/ggerganov/llama.cpp/pull/1087#issuecomment-1682807878
|
||||
# This is mostly tied to rocBLAS supported archs.
|
||||
ARG ROCM_DOCKER_ARCH="\
|
||||
gfx803 \
|
||||
gfx900 \
|
||||
gfx906 \
|
||||
gfx908 \
|
||||
gfx90a \
|
||||
gfx1010 \
|
||||
gfx1030 \
|
||||
gfx1100 \
|
||||
gfx1101 \
|
||||
gfx1102"
|
||||
|
||||
COPY requirements.txt requirements.txt
|
||||
COPY requirements requirements
|
||||
|
||||
RUN pip install --upgrade pip setuptools wheel \
|
||||
&& pip install -r requirements.txt
|
||||
|
||||
WORKDIR /app
|
||||
|
||||
COPY . .
|
||||
|
||||
# Set nvcc architecture
|
||||
ENV AMDGPU_TARGETS=${ROCM_DOCKER_ARCH}
|
||||
# Enable ROCm
|
||||
ENV GGML_HIPBLAS=1
|
||||
ENV CC=/opt/rocm/llvm/bin/clang
|
||||
ENV CXX=/opt/rocm/llvm/bin/clang++
|
||||
|
||||
RUN make -j$(nproc) llama-cli
|
||||
|
||||
ENTRYPOINT [ "/app/llama-cli" ]
|
||||
@ -1,27 +0,0 @@
|
||||
ARG UBUNTU_VERSION=jammy
|
||||
|
||||
FROM ubuntu:$UBUNTU_VERSION AS build
|
||||
|
||||
# Install build tools
|
||||
RUN apt update && apt install -y git build-essential cmake wget libgomp1
|
||||
|
||||
# Install Vulkan SDK
|
||||
RUN wget -qO - https://packages.lunarg.com/lunarg-signing-key-pub.asc | apt-key add - && \
|
||||
wget -qO /etc/apt/sources.list.d/lunarg-vulkan-jammy.list https://packages.lunarg.com/vulkan/lunarg-vulkan-jammy.list && \
|
||||
apt update -y && \
|
||||
apt-get install -y vulkan-sdk
|
||||
|
||||
# Build it
|
||||
WORKDIR /app
|
||||
COPY . .
|
||||
RUN cmake -B build -DGGML_NATIVE=OFF -DGGML_VULKAN=1 && \
|
||||
cmake --build build --config Release --target llama-cli
|
||||
|
||||
# Clean up
|
||||
WORKDIR /
|
||||
RUN cp /app/build/bin/llama-cli /llama-cli && \
|
||||
rm -rf /app
|
||||
|
||||
ENV LC_ALL=C.utf8
|
||||
|
||||
ENTRYPOINT [ "/llama-cli" ]
|
||||
@ -1,29 +0,0 @@
|
||||
ARG UBUNTU_VERSION=22.04
|
||||
|
||||
FROM ubuntu:$UBUNTU_VERSION AS build
|
||||
|
||||
RUN apt-get update && \
|
||||
apt-get install -y build-essential git cmake libcurl4-openssl-dev
|
||||
|
||||
WORKDIR /app
|
||||
|
||||
COPY . .
|
||||
|
||||
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
|
||||
|
||||
WORKDIR /app
|
||||
|
||||
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 [ "/app/llama-cli" ]
|
||||
@ -1,43 +0,0 @@
|
||||
ARG UBUNTU_VERSION=22.04
|
||||
# This needs to generally match the container host's environment.
|
||||
ARG CUDA_VERSION=12.6.0
|
||||
# Target the CUDA build image
|
||||
ARG BASE_CUDA_DEV_CONTAINER=nvidia/cuda:${CUDA_VERSION}-devel-ubuntu${UBUNTU_VERSION}
|
||||
# Target the CUDA runtime image
|
||||
ARG BASE_CUDA_RUN_CONTAINER=nvidia/cuda:${CUDA_VERSION}-runtime-ubuntu${UBUNTU_VERSION}
|
||||
|
||||
FROM ${BASE_CUDA_DEV_CONTAINER} AS build
|
||||
|
||||
# CUDA architecture to build for (defaults to all supported archs)
|
||||
ARG CUDA_DOCKER_ARCH=default
|
||||
|
||||
RUN apt-get update && \
|
||||
apt-get install -y build-essential git cmake libcurl4-openssl-dev
|
||||
|
||||
WORKDIR /app
|
||||
|
||||
COPY . .
|
||||
|
||||
# Use the default CUDA archs if not specified
|
||||
RUN if [ "${CUDA_DOCKER_ARCH}" != "default" ]; then \
|
||||
export CMAKE_ARGS="-DCMAKE_CUDA_ARCHITECTURES=${CUDA_DOCKER_ARCH}"; \
|
||||
fi && \
|
||||
cmake -B build -DGGML_NATIVE=OFF -DGGML_CUDA=ON -DLLAMA_CURL=ON ${CMAKE_ARGS} -DCMAKE_EXE_LINKER_FLAGS=-Wl,--allow-shlib-undefined . && \
|
||||
cmake --build build --config Release --target llama-server -j$(nproc) && \
|
||||
mkdir -p /app/lib && \
|
||||
find build -name "*.so" -exec cp {} /app/lib \;
|
||||
|
||||
FROM ${BASE_CUDA_RUN_CONTAINER} AS runtime
|
||||
|
||||
RUN apt-get update && \
|
||||
apt-get install -y libcurl4-openssl-dev libgomp1 curl
|
||||
|
||||
COPY --from=build /app/lib/ /
|
||||
COPY --from=build /app/build/bin/llama-server /llama-server
|
||||
|
||||
# Must be set to 0.0.0.0 so it can listen to requests from host machine
|
||||
ENV LLAMA_ARG_HOST=0.0.0.0
|
||||
|
||||
HEALTHCHECK CMD [ "curl", "-f", "http://localhost:8080/health" ]
|
||||
|
||||
ENTRYPOINT [ "/llama-server" ]
|
||||
@ -1,34 +0,0 @@
|
||||
ARG ONEAPI_VERSION=2025.0.0-0-devel-ubuntu22.04
|
||||
|
||||
FROM intel/oneapi-basekit:$ONEAPI_VERSION AS build
|
||||
|
||||
ARG GGML_SYCL_F16=OFF
|
||||
RUN apt-get update && \
|
||||
apt-get install -y git libcurl4-openssl-dev
|
||||
|
||||
WORKDIR /app
|
||||
|
||||
COPY . .
|
||||
|
||||
RUN if [ "${GGML_SYCL_F16}" = "ON" ]; then \
|
||||
echo "GGML_SYCL_F16 is set" && \
|
||||
export OPT_SYCL_F16="-DGGML_SYCL_F16=ON"; \
|
||||
fi && \
|
||||
echo "Building with dynamic libs" && \
|
||||
cmake -B build -DGGML_NATIVE=OFF -DGGML_SYCL=ON -DCMAKE_C_COMPILER=icx -DCMAKE_CXX_COMPILER=icpx -DLLAMA_CURL=ON ${OPT_SYCL_F16} && \
|
||||
cmake --build build --config Release --target llama-server
|
||||
|
||||
FROM intel/oneapi-basekit:$ONEAPI_VERSION AS runtime
|
||||
|
||||
RUN apt-get update && \
|
||||
apt-get install -y libcurl4-openssl-dev curl
|
||||
|
||||
COPY --from=build /app/build/bin/llama-server /llama-server
|
||||
|
||||
ENV LC_ALL=C.utf8
|
||||
# Must be set to 0.0.0.0 so it can listen to requests from host machine
|
||||
ENV LLAMA_ARG_HOST=0.0.0.0
|
||||
|
||||
HEALTHCHECK CMD [ "curl", "-f", "http://localhost:8080/health" ]
|
||||
|
||||
ENTRYPOINT [ "/llama-server" ]
|
||||
@ -1,43 +0,0 @@
|
||||
ARG UBUNTU_VERSION=22.04
|
||||
# This needs to generally match the container host's environment.
|
||||
ARG MUSA_VERSION=rc3.1.0
|
||||
# Target the MUSA build image
|
||||
ARG BASE_MUSA_DEV_CONTAINER=mthreads/musa:${MUSA_VERSION}-devel-ubuntu${UBUNTU_VERSION}
|
||||
# Target the MUSA runtime image
|
||||
ARG BASE_MUSA_RUN_CONTAINER=mthreads/musa:${MUSA_VERSION}-runtime-ubuntu${UBUNTU_VERSION}
|
||||
|
||||
FROM ${BASE_MUSA_DEV_CONTAINER} AS build
|
||||
|
||||
# MUSA architecture to build for (defaults to all supported archs)
|
||||
ARG MUSA_DOCKER_ARCH=default
|
||||
|
||||
RUN apt-get update && \
|
||||
apt-get install -y build-essential git cmake libcurl4-openssl-dev
|
||||
|
||||
WORKDIR /app
|
||||
|
||||
COPY . .
|
||||
|
||||
# Use the default MUSA archs if not specified
|
||||
RUN if [ "${MUSA_DOCKER_ARCH}" != "default" ]; then \
|
||||
export CMAKE_ARGS="-DMUSA_ARCHITECTURES=${MUSA_DOCKER_ARCH}"; \
|
||||
fi && \
|
||||
cmake -B build -DGGML_NATIVE=OFF -DGGML_MUSA=ON -DLLAMA_CURL=ON ${CMAKE_ARGS} -DCMAKE_EXE_LINKER_FLAGS=-Wl,--allow-shlib-undefined . && \
|
||||
cmake --build build --config Release --target llama-server -j$(nproc) && \
|
||||
mkdir -p /app/lib && \
|
||||
find build -name "*.so" -exec cp {} /app/lib \;
|
||||
|
||||
FROM ${BASE_MUSA_RUN_CONTAINER} AS runtime
|
||||
|
||||
RUN apt-get update && \
|
||||
apt-get install -y libcurl4-openssl-dev libgomp1 curl
|
||||
|
||||
COPY --from=build /app/lib/ /
|
||||
COPY --from=build /app/build/bin/llama-server /llama-server
|
||||
|
||||
# Must be set to 0.0.0.0 so it can listen to requests from host machine
|
||||
ENV LLAMA_ARG_HOST=0.0.0.0
|
||||
|
||||
HEALTHCHECK CMD [ "curl", "-f", "http://localhost:8080/health" ]
|
||||
|
||||
ENTRYPOINT [ "/llama-server" ]
|
||||
@ -1,54 +0,0 @@
|
||||
ARG UBUNTU_VERSION=22.04
|
||||
|
||||
# This needs to generally match the container host's environment.
|
||||
ARG ROCM_VERSION=5.6
|
||||
|
||||
# Target the CUDA build image
|
||||
ARG BASE_ROCM_DEV_CONTAINER=rocm/dev-ubuntu-${UBUNTU_VERSION}:${ROCM_VERSION}-complete
|
||||
|
||||
FROM ${BASE_ROCM_DEV_CONTAINER} AS build
|
||||
|
||||
# Unless otherwise specified, we make a fat build.
|
||||
# List from https://github.com/ggerganov/llama.cpp/pull/1087#issuecomment-1682807878
|
||||
# This is mostly tied to rocBLAS supported archs.
|
||||
ARG ROCM_DOCKER_ARCH="\
|
||||
gfx803 \
|
||||
gfx900 \
|
||||
gfx906 \
|
||||
gfx908 \
|
||||
gfx90a \
|
||||
gfx1010 \
|
||||
gfx1030 \
|
||||
gfx1100 \
|
||||
gfx1101 \
|
||||
gfx1102"
|
||||
|
||||
COPY requirements.txt requirements.txt
|
||||
COPY requirements requirements
|
||||
|
||||
RUN pip install --upgrade pip setuptools wheel \
|
||||
&& pip install -r requirements.txt
|
||||
|
||||
WORKDIR /app
|
||||
|
||||
COPY . .
|
||||
|
||||
# Set nvcc architecture
|
||||
ENV AMDGPU_TARGETS=${ROCM_DOCKER_ARCH}
|
||||
# Enable ROCm
|
||||
ENV GGML_HIPBLAS=1
|
||||
ENV CC=/opt/rocm/llvm/bin/clang
|
||||
ENV CXX=/opt/rocm/llvm/bin/clang++
|
||||
# Must be set to 0.0.0.0 so it can listen to requests from host machine
|
||||
ENV LLAMA_ARG_HOST=0.0.0.0
|
||||
|
||||
# Enable cURL
|
||||
ENV LLAMA_CURL=1
|
||||
RUN apt-get update && \
|
||||
apt-get install -y libcurl4-openssl-dev curl
|
||||
|
||||
RUN make -j$(nproc) llama-server
|
||||
|
||||
HEALTHCHECK CMD [ "curl", "-f", "http://localhost:8080/health" ]
|
||||
|
||||
ENTRYPOINT [ "/app/llama-server" ]
|
||||
@ -1,31 +0,0 @@
|
||||
ARG UBUNTU_VERSION=jammy
|
||||
|
||||
FROM ubuntu:$UBUNTU_VERSION AS build
|
||||
|
||||
# Install build tools
|
||||
RUN apt update && apt install -y git build-essential cmake wget
|
||||
|
||||
# Install Vulkan SDK and cURL
|
||||
RUN wget -qO - https://packages.lunarg.com/lunarg-signing-key-pub.asc | apt-key add - && \
|
||||
wget -qO /etc/apt/sources.list.d/lunarg-vulkan-jammy.list https://packages.lunarg.com/vulkan/lunarg-vulkan-jammy.list && \
|
||||
apt update -y && \
|
||||
apt-get install -y vulkan-sdk libcurl4-openssl-dev curl
|
||||
|
||||
# Build it
|
||||
WORKDIR /app
|
||||
COPY . .
|
||||
RUN cmake -B build -DGGML_NATIVE=OFF -DGGML_VULKAN=1 -DLLAMA_CURL=1 && \
|
||||
cmake --build build --config Release --target llama-server
|
||||
|
||||
# Clean up
|
||||
WORKDIR /
|
||||
RUN cp /app/build/bin/llama-server /llama-server && \
|
||||
rm -rf /app
|
||||
|
||||
ENV LC_ALL=C.utf8
|
||||
# Must be set to 0.0.0.0 so it can listen to requests from host machine
|
||||
ENV LLAMA_ARG_HOST=0.0.0.0
|
||||
|
||||
HEALTHCHECK CMD [ "curl", "-f", "http://localhost:8080/health" ]
|
||||
|
||||
ENTRYPOINT [ "/llama-server" ]
|
||||
@ -1,33 +0,0 @@
|
||||
ARG UBUNTU_VERSION=22.04
|
||||
|
||||
FROM ubuntu:$UBUNTU_VERSION AS build
|
||||
|
||||
RUN apt-get update && \
|
||||
apt-get install -y build-essential git cmake libcurl4-openssl-dev
|
||||
|
||||
WORKDIR /app
|
||||
|
||||
COPY . .
|
||||
|
||||
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
|
||||
|
||||
WORKDIR /app
|
||||
|
||||
RUN apt-get update && \
|
||||
apt-get install -y libcurl4-openssl-dev libgomp1 curl
|
||||
|
||||
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
|
||||
ENV LLAMA_ARG_HOST=0.0.0.0
|
||||
|
||||
HEALTHCHECK CMD [ "curl", "-f", "http://localhost:8080/health" ]
|
||||
|
||||
ENTRYPOINT [ "/app/llama-server" ]
|
||||
108
.devops/musa.Dockerfile
Normal file
108
.devops/musa.Dockerfile
Normal file
@ -0,0 +1,108 @@
|
||||
ARG UBUNTU_VERSION=22.04
|
||||
# This needs to generally match the container host's environment.
|
||||
ARG MUSA_VERSION=rc3.1.0
|
||||
# Target the MUSA build image
|
||||
ARG BASE_MUSA_DEV_CONTAINER=mthreads/musa:${MUSA_VERSION}-devel-ubuntu${UBUNTU_VERSION}
|
||||
|
||||
ARG BASE_MUSA_RUN_CONTAINER=mthreads/musa:${MUSA_VERSION}-runtime-ubuntu${UBUNTU_VERSION}
|
||||
|
||||
FROM ${BASE_MUSA_DEV_CONTAINER} AS build
|
||||
|
||||
# MUSA architecture to build for (defaults to all supported archs)
|
||||
ARG MUSA_DOCKER_ARCH=default
|
||||
|
||||
RUN apt-get update && \
|
||||
apt-get install -y \
|
||||
build-essential \
|
||||
cmake \
|
||||
python3 \
|
||||
python3-pip \
|
||||
git \
|
||||
libcurl4-openssl-dev \
|
||||
libgomp1
|
||||
|
||||
COPY requirements.txt requirements.txt
|
||||
COPY requirements requirements
|
||||
|
||||
RUN pip install --upgrade pip setuptools wheel \
|
||||
&& pip install -r requirements.txt
|
||||
|
||||
WORKDIR /app
|
||||
|
||||
COPY . .
|
||||
|
||||
# Use the default MUSA archs if not specified
|
||||
RUN if [ "${MUSA_DOCKER_ARCH}" != "default" ]; then \
|
||||
export CMAKE_ARGS="-DMUSA_ARCHITECTURES=${MUSA_DOCKER_ARCH}"; \
|
||||
fi && \
|
||||
cmake -B build -DGGML_NATIVE=OFF -DGGML_MUSA=ON -DLLAMA_CURL=ON ${CMAKE_ARGS} -DCMAKE_EXE_LINKER_FLAGS=-Wl,--allow-shlib-undefined . && \
|
||||
cmake --build build --config Release -j$(nproc)
|
||||
|
||||
RUN mkdir -p /app/lib && \
|
||||
find build -name "*.so" -exec cp {} /app/lib \;
|
||||
|
||||
RUN mkdir -p /app/full \
|
||||
&& cp build/bin/* /app/full \
|
||||
&& cp *.py /app/full \
|
||||
&& cp -r gguf-py /app/full \
|
||||
&& cp -r requirements /app/full \
|
||||
&& cp requirements.txt /app/full \
|
||||
&& cp .devops/tools.sh /app/full/tools.sh
|
||||
|
||||
## Base image
|
||||
FROM ${BASE_MUSA_RUN_CONTAINER} AS base
|
||||
|
||||
RUN apt-get update \
|
||||
&& apt-get install -y libgomp1 curl\
|
||||
&& apt autoremove -y \
|
||||
&& apt clean -y \
|
||||
&& rm -rf /tmp/* /var/tmp/* \
|
||||
&& find /var/cache/apt/archives /var/lib/apt/lists -not -name lock -type f -delete \
|
||||
&& find /var/cache -type f -delete
|
||||
|
||||
COPY --from=build /app/lib/ /app
|
||||
|
||||
### Full
|
||||
FROM base AS full
|
||||
|
||||
COPY --from=build /app/full /app
|
||||
|
||||
WORKDIR /app
|
||||
|
||||
RUN apt-get update \
|
||||
&& apt-get install -y \
|
||||
git \
|
||||
python3 \
|
||||
python3-pip \
|
||||
&& pip install --upgrade pip setuptools wheel \
|
||||
&& pip install -r requirements.txt \
|
||||
&& apt autoremove -y \
|
||||
&& apt clean -y \
|
||||
&& rm -rf /tmp/* /var/tmp/* \
|
||||
&& find /var/cache/apt/archives /var/lib/apt/lists -not -name lock -type f -delete \
|
||||
&& find /var/cache -type f -delete
|
||||
|
||||
|
||||
ENTRYPOINT ["/app/tools.sh"]
|
||||
|
||||
### Light, CLI only
|
||||
FROM base AS light
|
||||
|
||||
COPY --from=build /app/full/llama-cli /app
|
||||
|
||||
WORKDIR /app
|
||||
|
||||
ENTRYPOINT [ "/app/llama-cli" ]
|
||||
|
||||
### Server, Server only
|
||||
FROM base AS server
|
||||
|
||||
ENV LLAMA_ARG_HOST=0.0.0.0
|
||||
|
||||
COPY --from=build /app/full/llama-server /app
|
||||
|
||||
WORKDIR /app
|
||||
|
||||
HEALTHCHECK CMD [ "curl", "-f", "http://localhost:8080/health" ]
|
||||
|
||||
ENTRYPOINT [ "/app/llama-server" ]
|
||||
113
.devops/rocm.Dockerfile
Normal file
113
.devops/rocm.Dockerfile
Normal file
@ -0,0 +1,113 @@
|
||||
ARG UBUNTU_VERSION=24.04
|
||||
|
||||
# This needs to generally match the container host's environment.
|
||||
ARG ROCM_VERSION=6.3
|
||||
ARG AMDGPU_VERSION=6.3
|
||||
|
||||
# Target the CUDA build image
|
||||
ARG BASE_ROCM_DEV_CONTAINER=rocm/dev-ubuntu-${UBUNTU_VERSION}:${ROCM_VERSION}-complete
|
||||
|
||||
### Build image
|
||||
FROM ${BASE_ROCM_DEV_CONTAINER} AS build
|
||||
|
||||
# Unless otherwise specified, we make a fat build.
|
||||
# List from https://github.com/ggerganov/llama.cpp/pull/1087#issuecomment-1682807878
|
||||
# This is mostly tied to rocBLAS supported archs.
|
||||
# gfx803, gfx900, gfx1032, gfx1101, gfx1102,not officialy supported
|
||||
# gfx906 is deprecated
|
||||
#check https://rocm.docs.amd.com/projects/install-on-linux/en/docs-6.2.4/reference/system-requirements.html
|
||||
|
||||
#ARG ROCM_DOCKER_ARCH='gfx803,gfx900,gfx906,gfx908,gfx90a,gfx942,gfx1010,gfx1030,gfx1032,gfx1100,gfx1101,gfx1102'
|
||||
ARG ROCM_DOCKER_ARCH=gfx1100
|
||||
|
||||
# Set nvcc architectured
|
||||
ENV AMDGPU_TARGETS=${ROCM_DOCKER_ARCH}
|
||||
# Enable ROCm
|
||||
# ENV CC=/opt/rocm/llvm/bin/clang
|
||||
# ENV CXX=/opt/rocm/llvm/bin/clang++
|
||||
|
||||
RUN apt-get update \
|
||||
&& apt-get install -y \
|
||||
build-essential \
|
||||
cmake \
|
||||
git \
|
||||
libcurl4-openssl-dev \
|
||||
curl \
|
||||
libgomp1
|
||||
|
||||
WORKDIR /app
|
||||
|
||||
COPY . .
|
||||
|
||||
RUN HIPCXX="$(hipconfig -l)/clang" HIP_PATH="$(hipconfig -R)" \
|
||||
cmake -S . -B build -DGGML_HIP=ON -DAMDGPU_TARGETS=$ROCM_DOCKER_ARCH -DCMAKE_BUILD_TYPE=Release -DLLAMA_CURL=ON \
|
||||
&& cmake --build build --config Release -j$(nproc)
|
||||
|
||||
RUN mkdir -p /app/lib \
|
||||
&& find build -name "*.so" -exec cp {} /app/lib \;
|
||||
|
||||
RUN mkdir -p /app/full \
|
||||
&& cp build/bin/* /app/full \
|
||||
&& cp *.py /app/full \
|
||||
&& cp -r gguf-py /app/full \
|
||||
&& cp -r requirements /app/full \
|
||||
&& cp requirements.txt /app/full \
|
||||
&& cp .devops/tools.sh /app/full/tools.sh
|
||||
|
||||
## Base image
|
||||
FROM ${BASE_ROCM_DEV_CONTAINER} AS base
|
||||
|
||||
RUN apt-get update \
|
||||
&& apt-get install -y libgomp1 curl\
|
||||
&& apt autoremove -y \
|
||||
&& apt clean -y \
|
||||
&& rm -rf /tmp/* /var/tmp/* \
|
||||
&& find /var/cache/apt/archives /var/lib/apt/lists -not -name lock -type f -delete \
|
||||
&& find /var/cache -type f -delete
|
||||
|
||||
COPY --from=build /app/lib/ /app
|
||||
|
||||
### Full
|
||||
FROM base AS full
|
||||
|
||||
COPY --from=build /app/full /app
|
||||
|
||||
WORKDIR /app
|
||||
|
||||
RUN apt-get update \
|
||||
&& apt-get install -y \
|
||||
git \
|
||||
python3-pip \
|
||||
python3 \
|
||||
python3-wheel\
|
||||
&& pip install --break-system-packages --upgrade setuptools \
|
||||
&& pip install --break-system-packages -r requirements.txt \
|
||||
&& apt autoremove -y \
|
||||
&& apt clean -y \
|
||||
&& rm -rf /tmp/* /var/tmp/* \
|
||||
&& find /var/cache/apt/archives /var/lib/apt/lists -not -name lock -type f -delete \
|
||||
&& find /var/cache -type f -delete
|
||||
|
||||
ENTRYPOINT ["/app/tools.sh"]
|
||||
|
||||
### Light, CLI only
|
||||
FROM base AS light
|
||||
|
||||
COPY --from=build /app/full/llama-cli /app
|
||||
|
||||
WORKDIR /app
|
||||
|
||||
ENTRYPOINT [ "/app/llama-cli" ]
|
||||
|
||||
### Server, Server only
|
||||
FROM base AS server
|
||||
|
||||
ENV LLAMA_ARG_HOST=0.0.0.0
|
||||
|
||||
COPY --from=build /app/full/llama-server /app
|
||||
|
||||
WORKDIR /app
|
||||
|
||||
HEALTHCHECK CMD [ "curl", "-f", "http://localhost:8080/health" ]
|
||||
|
||||
ENTRYPOINT [ "/app/llama-server" ]
|
||||
88
.devops/vulkan.Dockerfile
Normal file
88
.devops/vulkan.Dockerfile
Normal file
@ -0,0 +1,88 @@
|
||||
ARG UBUNTU_VERSION=jammy
|
||||
|
||||
FROM ubuntu:$UBUNTU_VERSION AS build
|
||||
|
||||
# Install build tools
|
||||
RUN apt update && apt install -y git build-essential cmake wget
|
||||
|
||||
# Install Vulkan SDK and cURL
|
||||
RUN wget -qO - https://packages.lunarg.com/lunarg-signing-key-pub.asc | apt-key add - && \
|
||||
wget -qO /etc/apt/sources.list.d/lunarg-vulkan-jammy.list https://packages.lunarg.com/vulkan/lunarg-vulkan-jammy.list && \
|
||||
apt update -y && \
|
||||
apt-get install -y vulkan-sdk libcurl4-openssl-dev curl
|
||||
|
||||
# Build it
|
||||
WORKDIR /app
|
||||
|
||||
COPY . .
|
||||
|
||||
RUN cmake -B build -DGGML_NATIVE=OFF -DGGML_VULKAN=1 -DLLAMA_CURL=1 && \
|
||||
cmake --build build --config Release -j$(nproc)
|
||||
|
||||
RUN mkdir -p /app/lib && \
|
||||
find build -name "*.so" -exec cp {} /app/lib \;
|
||||
|
||||
RUN mkdir -p /app/full \
|
||||
&& cp build/bin/* /app/full \
|
||||
&& cp *.py /app/full \
|
||||
&& cp -r gguf-py /app/full \
|
||||
&& cp -r requirements /app/full \
|
||||
&& cp requirements.txt /app/full \
|
||||
&& cp .devops/tools.sh /app/full/tools.sh
|
||||
|
||||
## Base image
|
||||
FROM ubuntu:$UBUNTU_VERSION AS base
|
||||
|
||||
RUN apt-get update \
|
||||
&& apt-get install -y libgomp1 curl\
|
||||
&& apt autoremove -y \
|
||||
&& apt clean -y \
|
||||
&& rm -rf /tmp/* /var/tmp/* \
|
||||
&& find /var/cache/apt/archives /var/lib/apt/lists -not -name lock -type f -delete \
|
||||
&& find /var/cache -type f -delete
|
||||
|
||||
COPY --from=build /app/lib/ /app
|
||||
|
||||
### Full
|
||||
FROM base AS full
|
||||
|
||||
COPY --from=build /app/full /app
|
||||
|
||||
WORKDIR /app
|
||||
|
||||
RUN apt-get update \
|
||||
&& apt-get install -y \
|
||||
git \
|
||||
python3 \
|
||||
python3-pip \
|
||||
&& pip install --upgrade pip setuptools wheel \
|
||||
&& pip install -r requirements.txt \
|
||||
&& apt autoremove -y \
|
||||
&& apt clean -y \
|
||||
&& rm -rf /tmp/* /var/tmp/* \
|
||||
&& find /var/cache/apt/archives /var/lib/apt/lists -not -name lock -type f -delete \
|
||||
&& find /var/cache -type f -delete
|
||||
|
||||
ENTRYPOINT ["/app/tools.sh"]
|
||||
|
||||
### Light, CLI only
|
||||
FROM base AS light
|
||||
|
||||
COPY --from=build /app/full/llama-cli /app
|
||||
|
||||
WORKDIR /app
|
||||
|
||||
ENTRYPOINT [ "/app/llama-cli" ]
|
||||
|
||||
### Server, Server only
|
||||
FROM base AS server
|
||||
|
||||
ENV LLAMA_ARG_HOST=0.0.0.0
|
||||
|
||||
COPY --from=build /app/full/llama-server /app
|
||||
|
||||
WORKDIR /app
|
||||
|
||||
HEALTHCHECK CMD [ "curl", "-f", "http://localhost:8080/health" ]
|
||||
|
||||
ENTRYPOINT [ "/app/llama-server" ]
|
||||
104
.github/workflows/docker.yml
vendored
104
.github/workflows/docker.yml
vendored
@ -34,21 +34,14 @@ jobs:
|
||||
strategy:
|
||||
matrix:
|
||||
config:
|
||||
- { tag: "light", dockerfile: ".devops/llama-cli.Dockerfile", platforms: "linux/amd64,linux/arm64" }
|
||||
- { tag: "server", dockerfile: ".devops/llama-server.Dockerfile", platforms: "linux/amd64,linux/arm64" }
|
||||
- { tag: "full", dockerfile: ".devops/full.Dockerfile", platforms: "linux/amd64,linux/arm64" }
|
||||
- { tag: "light-cuda", dockerfile: ".devops/llama-cli-cuda.Dockerfile", platforms: "linux/amd64" }
|
||||
- { tag: "server-cuda", dockerfile: ".devops/llama-server-cuda.Dockerfile", platforms: "linux/amd64" }
|
||||
- { tag: "full-cuda", dockerfile: ".devops/full-cuda.Dockerfile", platforms: "linux/amd64" }
|
||||
- { tag: "light-musa", dockerfile: ".devops/llama-cli-musa.Dockerfile", platforms: "linux/amd64" }
|
||||
- { tag: "server-musa", dockerfile: ".devops/llama-server-musa.Dockerfile", platforms: "linux/amd64" }
|
||||
- { tag: "full-musa", dockerfile: ".devops/full-musa.Dockerfile", platforms: "linux/amd64" }
|
||||
# Multi-stage build
|
||||
- { tag: "cpu", dockerfile: ".devops/cpu.Dockerfile", platforms: "linux/amd64,linux/arm64", full: true, light: true, server: true, freediskspace: false}
|
||||
- { tag: "cuda", dockerfile: ".devops/cuda.Dockerfile", platforms: "linux/amd64", full: true, light: true, server: true, freediskspace: false}
|
||||
- { tag: "musa", dockerfile: ".devops/musa.Dockerfile", platforms: "linux/amd64", full: true, light: true, server: true, freediskspace: false}
|
||||
- { tag: "intel", dockerfile: ".devops/intel.Dockerfile", platforms: "linux/amd64", full: true, light: true, server: true, freediskspace: false}
|
||||
- { tag: "vulkan", dockerfile: ".devops/vulkan.Dockerfile", platforms: "linux/amd64", full: true, light: true, server: true, freediskspace: false}
|
||||
# Note: the rocm images are failing due to a compiler error and are disabled until this is fixed to allow the workflow to complete
|
||||
#- { tag: "light-rocm", dockerfile: ".devops/llama-cli-rocm.Dockerfile", platforms: "linux/amd64,linux/arm64" }
|
||||
#- { tag: "server-rocm", dockerfile: ".devops/llama-server-rocm.Dockerfile", platforms: "linux/amd64,linux/arm64" }
|
||||
#- { tag: "full-rocm", dockerfile: ".devops/full-rocm.Dockerfile", platforms: "linux/amd64,linux/arm64" }
|
||||
- { tag: "light-intel", dockerfile: ".devops/llama-cli-intel.Dockerfile", platforms: "linux/amd64" }
|
||||
- { tag: "server-intel", dockerfile: ".devops/llama-server-intel.Dockerfile", platforms: "linux/amd64" }
|
||||
#- {tag: "rocm", dockerfile: ".devops/rocm.Dockerfile", platforms: "linux/amd64,linux/arm64", full: true, light: true, server: true, freediskspace: true }
|
||||
steps:
|
||||
- name: Check out the repo
|
||||
uses: actions/checkout@v4
|
||||
@ -56,10 +49,10 @@ jobs:
|
||||
fetch-depth: 0 # preserve git history, so we can determine the build number
|
||||
|
||||
- name: Set up QEMU
|
||||
uses: docker/setup-qemu-action@v2
|
||||
uses: docker/setup-qemu-action@v3
|
||||
|
||||
- name: Set up Docker Buildx
|
||||
uses: docker/setup-buildx-action@v2
|
||||
uses: docker/setup-buildx-action@v3
|
||||
|
||||
- name: Log in to Docker Hub
|
||||
uses: docker/login-action@v2
|
||||
@ -79,25 +72,34 @@ jobs:
|
||||
|
||||
# determine tag name postfix (build number, commit hash)
|
||||
if [[ "${{ env.GITHUB_BRANCH_NAME }}" == "master" ]]; then
|
||||
TAG_POSTFIX="b${BUILD_NUMBER}"
|
||||
TAG_POSTFIX="-b${BUILD_NUMBER}"
|
||||
else
|
||||
SAFE_NAME=$(echo "${{ env.GITHUB_BRANCH_NAME }}" | tr '/' '-')
|
||||
TAG_POSTFIX="${SAFE_NAME}-${SHORT_HASH}"
|
||||
TAG_POSTFIX="-${SAFE_NAME}-${SHORT_HASH}"
|
||||
fi
|
||||
|
||||
# list all tags possible
|
||||
TAGS=""
|
||||
TAGS="${TAGS}ghcr.io/${REPO_OWNER}/${REPO_NAME}:${{ matrix.config.tag }},"
|
||||
TAGS="${TAGS}ghcr.io/${REPO_OWNER}/${REPO_NAME}:${{ matrix.config.tag }}-${TAG_POSTFIX}"
|
||||
|
||||
echo "output_tags=$TAGS" >> $GITHUB_OUTPUT
|
||||
echo "output_tags=$TAGS" # print out for debugging
|
||||
if [[ "${{ matrix.config.tag }}" == "cpu" ]]; then
|
||||
TYPE=""
|
||||
else
|
||||
TYPE="-${{ matrix.config.tag }}"
|
||||
fi
|
||||
PREFIX="ghcr.io/${REPO_OWNER}/${REPO_NAME}:"
|
||||
FULLTAGS="${PREFIX}full${TYPE},${PREFIX}full${TYPE}${TAG_POSTFIX}"
|
||||
LIGHTTAGS="${PREFIX}light${TYPE},${PREFIX}light${TYPE}${TAG_POSTFIX}"
|
||||
SERVERTAGS="${PREFIX}server${TYPE},${PREFIX}server${TYPE}${TAG_POSTFIX}"
|
||||
echo "full_output_tags=$FULLTAGS" >> $GITHUB_OUTPUT
|
||||
echo "light_output_tags=$LIGHTTAGS" >> $GITHUB_OUTPUT
|
||||
echo "server_output_tags=$SERVERTAGS" >> $GITHUB_OUTPUT
|
||||
echo "full_output_tags=$FULLTAGS" # print out for debugging
|
||||
echo "light_output_tags=$LIGHTTAGS" # print out for debugging
|
||||
echo "server_output_tags=$SERVERTAGS" # print out for debugging
|
||||
env:
|
||||
GITHUB_BRANCH_NAME: ${{ github.head_ref || github.ref_name }}
|
||||
GITHUB_REPOSITORY_OWNER: '${{ github.repository_owner }}'
|
||||
|
||||
# https://github.com/jlumbroso/free-disk-space/tree/54081f138730dfa15788a46383842cd2f914a1be#example
|
||||
- name: Free Disk Space (Ubuntu)
|
||||
if: ${{ matrix.config.free_disk_space == true }}
|
||||
uses: jlumbroso/free-disk-space@main
|
||||
with:
|
||||
# this might remove tools that are actually needed,
|
||||
@ -113,13 +115,59 @@ jobs:
|
||||
docker-images: true
|
||||
swap-storage: true
|
||||
|
||||
- name: Build and push Docker image (tagged + versioned)
|
||||
if: ${{ github.event_name == 'push' || github.event_name == 'schedule' || github.event_name == 'workflow_dispatch' }}
|
||||
- name: Build and push Full Docker image (tagged + versioned)
|
||||
if: ${{ (github.event_name == 'push' || github.event_name == 'schedule' || github.event_name == 'workflow_dispatch') && matrix.config.full == true }}
|
||||
uses: docker/build-push-action@v6
|
||||
with:
|
||||
context: .
|
||||
push: true
|
||||
platforms: ${{ matrix.config.platforms }}
|
||||
# tag list is generated from step above
|
||||
tags: ${{ steps.tag.outputs.output_tags }}
|
||||
tags: ${{ steps.tag.outputs.full_output_tags }}
|
||||
file: ${{ matrix.config.dockerfile }}
|
||||
target: full
|
||||
provenance: false
|
||||
# using github experimental cache
|
||||
cache-from: type=gha
|
||||
cache-to: type=gha,mode=max
|
||||
# return to this if the experimental github cache is having issues
|
||||
#cache-to: type=local,dest=/tmp/.buildx-cache
|
||||
#cache-from: type=local,src=/tmp/.buildx-cache
|
||||
|
||||
- name: Build and push Light Docker image (tagged + versioned)
|
||||
if: ${{ (github.event_name == 'push' || github.event_name == 'schedule' || github.event_name == 'workflow_dispatch') && matrix.config.light == true }}
|
||||
uses: docker/build-push-action@v6
|
||||
with:
|
||||
context: .
|
||||
push: true
|
||||
platforms: ${{ matrix.config.platforms }}
|
||||
# tag list is generated from step above
|
||||
tags: ${{ steps.tag.outputs.light_output_tags }}
|
||||
file: ${{ matrix.config.dockerfile }}
|
||||
target: light
|
||||
provenance: false
|
||||
# using github experimental cache
|
||||
cache-from: type=gha
|
||||
cache-to: type=gha,mode=max
|
||||
# return to this if the experimental github cache is having issues
|
||||
#cache-to: type=local,dest=/tmp/.buildx-cache
|
||||
#cache-from: type=local,src=/tmp/.buildx-cache
|
||||
|
||||
- name: Build and push Server Docker image (tagged + versioned)
|
||||
if: ${{ (github.event_name == 'push' || github.event_name == 'schedule' || github.event_name == 'workflow_dispatch') && matrix.config.server == true }}
|
||||
uses: docker/build-push-action@v6
|
||||
with:
|
||||
context: .
|
||||
push: true
|
||||
platforms: ${{ matrix.config.platforms }}
|
||||
# tag list is generated from step above
|
||||
tags: ${{ steps.tag.outputs.server_output_tags }}
|
||||
file: ${{ matrix.config.dockerfile }}
|
||||
target: server
|
||||
provenance: false
|
||||
# using github experimental cache
|
||||
cache-from: type=gha
|
||||
cache-to: type=gha,mode=max
|
||||
# return to this if the experimental github cache is having issues
|
||||
#cache-to: type=local,dest=/tmp/.buildx-cache
|
||||
#cache-from: type=local,src=/tmp/.buildx-cache
|
||||
|
||||
Loading…
Reference in New Issue
Block a user