next build (#8539)

* add build to .dockerignore * test: only build one arch * add build to .gitignore * fix ccache path * filter amdgpu targets * only filter if autodetecting * Don't clobber gpu list for default runner This ensures the GPU specific environment variables are set properly * explicitly set CXX compiler for HIP * Update build_windows.ps1 This isn't complete, but is close. Dependencies are missing, and it only builds the "default" preset. * build: add ollama subdir * add .git to .dockerignore * docs: update development.md * update build_darwin.sh * remove unused scripts * llm: add cwd and build/lib/ollama to library paths * default DYLD_LIBRARY_PATH to LD_LIBRARY_PATH in runner on macOS * add additional cmake output vars for msvc * interim edits to make server detection logic work with dll directories like lib/ollama/cuda_v12 * remove unncessary filepath.Dir, cleanup * add hardware-specific directory to path * use absolute server path * build: linux arm * cmake install targets * remove unused files * ml: visit each library path once * build: skip cpu variants on arm * build: install cpu targets * build: fix workflow * shorter names * fix rocblas install * docs: clean up development.md * consistent build dir removal in development.md * silence -Wimplicit-function-declaration build warnings in ggml-cpu * update readme * update development readme * llm: update library lookup logic now that there is one runner (#8587) * tweak development.md * update docs * add windows cuda/rocm tests --------- Co-authored-by: jmorganca <jmorganca@gmail.com> Co-authored-by: Daniel Hiltgen <daniel@ollama.com>
2025-12-10 07:46:59 +00:00 · 2025-01-29 15:03:38 -08:00
parent 2ef3c803a1
commit dcfb7a105c
542 changed files with 5796 additions and 11469 deletions
--- a/281
+++ b/281
@@ -1,201 +1,128 @@
-ARG GOLANG_VERSION=1.22.8
-ARG CUDA_VERSION_11=11.3.1
-ARG CUDA_VERSION_12=12.4.0
-ARG ROCM_VERSION=6.1.2
-ARG JETPACK_6=r36.2.0
-ARG JETPACK_5=r35.4.1
+# vim: filetype=dockerfile

-### To create a local image for building linux binaries on mac or windows with efficient incremental builds
-#
-# docker build --platform linux/amd64 -t builder-amd64 -f Dockerfile --target unified-builder-amd64 .
-# docker run --platform linux/amd64 --rm -it -v $(pwd):/go/src/github.com/ollama/ollama/ builder-amd64
-#
-### Then incremental builds will be much faster in this container
-#
-# make -j 10 dist
-#
-FROM --platform=linux/amd64 rocm/dev-centos-7:${ROCM_VERSION}-complete AS unified-builder-amd64
-ARG GOLANG_VERSION
-ARG CUDA_VERSION_11
-ARG CUDA_VERSION_12
-COPY ./scripts/rh_linux_deps.sh /
-ENV PATH /opt/rh/devtoolset-10/root/usr/bin:/usr/local/cuda/bin:$PATH
-ENV LD_LIBRARY_PATH=${LD_LIBRARY_PATH}:/usr/local/cuda/lib64
-RUN GOLANG_VERSION=${GOLANG_VERSION} sh /rh_linux_deps.sh
-RUN yum-config-manager --add-repo https://developer.download.nvidia.com/compute/cuda/repos/rhel7/x86_64/cuda-rhel7.repo && \
-    dnf clean all && \
-    dnf install -y \
-    zsh \
-    cuda-toolkit-$(echo ${CUDA_VERSION_11} | cut -f1-2 -d. | sed -e "s/\./-/g") \
-    cuda-toolkit-$(echo ${CUDA_VERSION_12} | cut -f1-2 -d. | sed -e "s/\./-/g")
-# TODO intel oneapi goes here...
-ENV GOARCH amd64
-ENV CGO_ENABLED 1
-WORKDIR /go/src/github.com/ollama/ollama/
-ENTRYPOINT [ "zsh" ]
+ARG FLAVOR=${TARGETARCH}

-### To create a local image for building linux binaries on mac or linux/arm64 with efficient incremental builds
-# Note: this does not contain jetson variants
-#
-# docker build --platform linux/arm64 -t builder-arm64 -f Dockerfile --target unified-builder-arm64 .
-# docker run --platform linux/arm64 --rm -it -v $(pwd):/go/src/github.com/ollama/ollama/ builder-arm64
-#
-FROM --platform=linux/arm64 rockylinux:8 AS unified-builder-arm64
-ARG GOLANG_VERSION
-ARG CUDA_VERSION_11
-ARG CUDA_VERSION_12
-COPY ./scripts/rh_linux_deps.sh /
-RUN GOLANG_VERSION=${GOLANG_VERSION} sh /rh_linux_deps.sh
-RUN yum-config-manager --add-repo https://developer.download.nvidia.com/compute/cuda/repos/rhel8/sbsa/cuda-rhel8.repo && \
-    dnf config-manager --set-enabled appstream && \
-    dnf clean all && \
-    dnf install -y \
-    zsh \
-    cuda-toolkit-$(echo ${CUDA_VERSION_11} | cut -f1-2 -d. | sed -e "s/\./-/g") \
-    cuda-toolkit-$(echo ${CUDA_VERSION_12} | cut -f1-2 -d. | sed -e "s/\./-/g")
-ENV PATH /opt/rh/gcc-toolset-10/root/usr/bin:$PATH:/usr/local/cuda/bin
-ENV LD_LIBRARY_PATH=${LD_LIBRARY_PATH}:/usr/local/cuda/lib64
-ENV LIBRARY_PATH=/usr/local/cuda/lib64/stubs:/opt/amdgpu/lib64
-ENV GOARCH arm64
-ENV CGO_ENABLED 1
-WORKDIR /go/src/github.com/ollama/ollama/
-ENTRYPOINT [ "zsh" ]
+ARG ROCMVERSION=6.1.2
+ARG JETPACK5VERSION=r35.4.1
+ARG JETPACK6VERSION=r36.2.0
+ARG CMAKEVERSION=3.31.2

-FROM --platform=linux/amd64 unified-builder-amd64 AS build-amd64
-COPY . .
-ARG OLLAMA_SKIP_CUDA_GENERATE
-ARG OLLAMA_SKIP_ROCM_GENERATE
-ARG OLLAMA_FAST_BUILD
-ARG VERSION
-ARG CUSTOM_CPU_FLAGS
+FROM --platform=linux/amd64 rocm/dev-centos-7:${ROCMVERSION}-complete AS base-amd64
+RUN sed -i -e 's/mirror.centos.org/vault.centos.org/g' -e 's/^#.*baseurl=http/baseurl=http/g' -e 's/^mirrorlist=http/#mirrorlist=http/g' /etc/yum.repos.d/*.repo \
+    && yum install -y yum-utils devtoolset-10-gcc devtoolset-10-gcc-c++ \
+    && yum-config-manager --add-repo https://developer.download.nvidia.com/compute/cuda/repos/rhel7/x86_64/cuda-rhel7.repo \
+    && curl -s -L https://github.com/ccache/ccache/releases/download/v4.10.2/ccache-4.10.2-linux-x86_64.tar.xz | tar -Jx -C /usr/local/bin --strip-components 1
+ENV PATH=/opt/rh/devtoolset-10/root/usr/bin:/opt/rh/devtoolset-11/root/usr/bin:$PATH
+
+FROM --platform=linux/arm64 rockylinux:8 AS base-arm64
+# install epel-release for ccache
+RUN yum install -y yum-utils epel-release \
+    && yum install -y clang ccache \
+    && yum-config-manager --add-repo https://developer.download.nvidia.com/compute/cuda/repos/rhel8/sbsa/cuda-rhel8.repo
+ENV CC=clang CXX=clang++
+
+FROM base-${TARGETARCH} AS base
+ARG CMAKEVERSION
+RUN curl -fsSL https://github.com/Kitware/CMake/releases/download/v${CMAKEVERSION}/cmake-${CMAKEVERSION}-linux-$(uname -m).tar.gz | tar xz -C /usr/local --strip-components 1
+COPY CMakeLists.txt CMakePresets.json .
+COPY ml/backend/ggml/ggml ml/backend/ggml/ggml
+ENV LDFLAGS=-s
+
+FROM base AS cpu
+# amd64 uses gcc which requires devtoolset-11 for AVX extensions while arm64 uses clang
+RUN if [ "$(uname -m)" = "x86_64" ]; then yum install -y devtoolset-11-gcc devtoolset-11-gcc-c++; fi
+ENV PATH=/opt/rh/devtoolset-11/root/usr/bin:$PATH
 RUN --mount=type=cache,target=/root/.ccache \
-    if grep "^flags" /proc/cpuinfo|grep avx>/dev/null; then \
-        make -j $(nproc) dist ; \
-    else \
-        make -j 5 dist ; \
-    fi
-RUN cd dist/linux-$GOARCH && \
-    tar -cf - . | pigz --best > ../ollama-linux-$GOARCH.tgz
-RUN if [ -z ${OLLAMA_SKIP_ROCM_GENERATE} ] ; then \
-    cd dist/linux-$GOARCH-rocm && \
-    tar -cf - . | pigz --best > ../ollama-linux-$GOARCH-rocm.tgz ;\
-    fi
+    cmake --preset 'CPU' \
+        && cmake --build --parallel --preset 'CPU' \
+        && cmake --install build --component CPU --strip --parallel 8

-# Jetsons need to be built in discrete stages
-FROM --platform=linux/arm64 nvcr.io/nvidia/l4t-jetpack:${JETPACK_5} AS runners-jetpack5-arm64
-ARG GOLANG_VERSION
-RUN apt-get update && apt-get install -y git curl ccache && \
-    curl -s -L https://dl.google.com/go/go${GOLANG_VERSION}.linux-arm64.tar.gz | tar xz -C /usr/local && \
-    ln -s /usr/local/go/bin/go /usr/local/bin/go && \
-    ln -s /usr/local/go/bin/gofmt /usr/local/bin/gofmt && \
-    apt-get clean && rm -rf /var/lib/apt/lists/*
-WORKDIR /go/src/github.com/ollama/ollama/
-COPY . .
-ARG CGO_CFLAGS
-ENV GOARCH arm64
-ARG VERSION
+FROM base AS cuda-11
+ARG CUDA11VERSION=11.3
+RUN yum install -y cuda-toolkit-${CUDA11VERSION//./-}
+ENV PATH=/usr/local/cuda-11/bin:$PATH
 RUN --mount=type=cache,target=/root/.ccache \
-    make -j 5 dist_cuda_v11 \
-        CUDA_ARCHITECTURES="72;87" \
-        GPU_RUNNER_VARIANT=_jetpack5 \
-        DIST_LIB_DIR=/go/src/github.com/ollama/ollama/dist/linux-arm64-jetpack5/lib/ollama \
-        DIST_GPU_RUNNER_DEPS_DIR=/go/src/github.com/ollama/ollama/dist/linux-arm64-jetpack5/lib/ollama/cuda_jetpack5
+    cmake --preset 'CUDA 11' \
+        && cmake --build --parallel --preset 'CUDA 11' \
+        && cmake --install build --component CUDA --strip --parallel 8

-FROM --platform=linux/arm64 nvcr.io/nvidia/l4t-jetpack:${JETPACK_6} AS runners-jetpack6-arm64
-ARG GOLANG_VERSION
-RUN apt-get update && apt-get install -y git curl ccache && \
-    curl -s -L https://dl.google.com/go/go${GOLANG_VERSION}.linux-arm64.tar.gz | tar xz -C /usr/local && \
-    ln -s /usr/local/go/bin/go /usr/local/bin/go && \
-    ln -s /usr/local/go/bin/gofmt /usr/local/bin/gofmt && \
-    apt-get clean && rm -rf /var/lib/apt/lists/*
-WORKDIR /go/src/github.com/ollama/ollama/
-COPY . .
-ARG CGO_CFLAGS
-ENV GOARCH arm64
-ARG VERSION
+FROM base AS cuda-12
+ARG CUDA12VERSION=12.4
+RUN yum install -y cuda-toolkit-${CUDA12VERSION//./-}
+ENV PATH=/usr/local/cuda-12/bin:$PATH
 RUN --mount=type=cache,target=/root/.ccache \
-    make -j 5 dist_cuda_v12 \
-        CUDA_ARCHITECTURES="87" \
-        GPU_RUNNER_VARIANT=_jetpack6 \
-        DIST_LIB_DIR=/go/src/github.com/ollama/ollama/dist/linux-arm64-jetpack6/lib/ollama \
-        DIST_GPU_RUNNER_DEPS_DIR=/go/src/github.com/ollama/ollama/dist/linux-arm64-jetpack6/lib/ollama/cuda_jetpack6
+    cmake --preset 'CUDA 12' \
+        && cmake --build --parallel --preset 'CUDA 12' \
+        && cmake --install build --component CUDA --strip --parallel 8

-FROM --platform=linux/arm64 unified-builder-arm64 AS build-arm64
-COPY . .
-ARG OLLAMA_SKIP_CUDA_GENERATE
-ARG OLLAMA_FAST_BUILD
-ARG VERSION
+FROM base AS rocm-6
 RUN --mount=type=cache,target=/root/.ccache \
-    make -j 5 dist
-COPY --from=runners-jetpack5-arm64 /go/src/github.com/ollama/ollama/dist/ dist/
-COPY --from=runners-jetpack6-arm64 /go/src/github.com/ollama/ollama/dist/ dist/
-RUN cd dist/linux-$GOARCH && \
-    tar -cf - . | pigz --best > ../ollama-linux-$GOARCH.tgz
-RUN cd dist/linux-$GOARCH-jetpack5 && \
-    tar -cf - . | pigz --best > ../ollama-linux-$GOARCH-jetpack5.tgz
-RUN cd dist/linux-$GOARCH-jetpack6 && \
-    tar -cf - . | pigz --best > ../ollama-linux-$GOARCH-jetpack6.tgz
+    cmake --preset 'ROCm 6' \
+        && cmake --build --parallel --preset 'ROCm 6' \
+        && cmake --install build --component HIP --strip --parallel 8

-FROM --platform=linux/amd64 scratch AS dist-amd64
-COPY --from=build-amd64 /go/src/github.com/ollama/ollama/dist/ollama-linux-*.tgz /
-FROM --platform=linux/arm64 scratch AS dist-arm64
-COPY --from=build-arm64 /go/src/github.com/ollama/ollama/dist/ollama-linux-*.tgz /
-FROM dist-$TARGETARCH AS dist
+FROM --platform=linux/arm64 nvcr.io/nvidia/l4t-jetpack:${JETPACK5VERSION} AS jetpack-5
+ARG CMAKEVERSION
+RUN apt-get update && apt-get install -y curl ccache \
+    && curl -fsSL https://github.com/Kitware/CMake/releases/download/v${CMAKEVERSION}/cmake-${CMAKEVERSION}-linux-$(uname -m).tar.gz | tar xz -C /usr/local --strip-components 1
+COPY CMakeLists.txt CMakePresets.json .
+COPY ml/backend/ggml/ggml ml/backend/ggml/ggml
+RUN --mount=type=cache,target=/root/.ccache \
+    cmake --preset 'JetPack 5' \
+        && cmake --build --parallel --preset 'JetPack 5' \
+        && cmake --install build --component CUDA --strip --parallel 8

+FROM --platform=linux/arm64 nvcr.io/nvidia/l4t-jetpack:${JETPACK6VERSION} AS jetpack-6
+ARG CMAKEVERSION
+RUN apt-get update && apt-get install -y curl ccache \
+    && curl -fsSL https://github.com/Kitware/CMake/releases/download/v${CMAKEVERSION}/cmake-${CMAKEVERSION}-linux-$(uname -m).tar.gz | tar xz -C /usr/local --strip-components 1
+COPY CMakeLists.txt CMakePresets.json .
+COPY ml/backend/ggml/ggml ml/backend/ggml/ggml
+RUN --mount=type=cache,target=/root/.ccache \
+    cmake --preset 'JetPack 6' \
+        && cmake --build --parallel --preset 'JetPack 6' \
+        && cmake --install build --component CUDA --strip --parallel 8

-# For amd64 container images, filter out cuda/rocm to minimize size
-FROM build-amd64 AS runners-cuda-amd64
-RUN rm -rf \
-    ./dist/linux-amd64/lib/ollama/libggml_hipblas.so \
-    ./dist/linux-amd64/lib/ollama/runners/rocm*
+FROM base AS build
+ARG GOVERSION=1.23.4
+RUN curl -fsSL https://golang.org/dl/go${GOVERSION}.linux-$(case $(uname -m) in x86_64) echo amd64 ;; aarch64) echo arm64 ;; esac).tar.gz | tar xz -C /usr/local
+ENV PATH=/usr/local/go/bin:$PATH
+WORKDIR /go/src/github.com/ollama/ollama
+COPY . .
+ARG GOFLAGS="'-ldflags=-w -s'"
+ENV CGO_ENABLED=1
+RUN --mount=type=cache,target=/root/.cache/go-build \
+    go build -trimpath -buildmode=pie -o /bin/ollama .

-FROM build-amd64 AS runners-rocm-amd64
-RUN rm -rf \
-    ./dist/linux-amd64/lib/ollama/libggml_cuda*.so \
-    ./dist/linux-amd64/lib/ollama/libcu*.so* \
-    ./dist/linux-amd64/lib/ollama/runners/cuda*
+FROM --platform=linux/amd64 scratch AS amd64
+COPY --from=cuda-11 dist/lib/ollama/cuda_v11 /lib/ollama/cuda_v11
+COPY --from=cuda-12 dist/lib/ollama/cuda_v12 /lib/ollama/cuda_v12

-FROM --platform=linux/amd64 ubuntu:22.04 AS runtime-amd64
-RUN apt-get update && \
-    apt-get install -y ca-certificates && \
-    apt-get clean && rm -rf /var/lib/apt/lists/*
-COPY --from=build-amd64 /go/src/github.com/ollama/ollama/dist/linux-amd64/bin/ /bin/
-COPY --from=runners-cuda-amd64 /go/src/github.com/ollama/ollama/dist/linux-amd64/lib/ /lib/
+FROM --platform=linux/arm64 scratch AS arm64
+COPY --from=cuda-11 dist/lib/ollama/cuda_v11 /lib/ollama/cuda_v11
+COPY --from=cuda-12 dist/lib/ollama/cuda_v12 /lib/ollama/cuda_v12
+COPY --from=jetpack-5 dist/lib/ollama/cuda_v11 lib/ollama/cuda_jetpack5
+COPY --from=jetpack-6 dist/lib/ollama/cuda_v12 lib/ollama/cuda_jetpack6

-FROM --platform=linux/arm64 ubuntu:22.04 AS runtime-arm64
-RUN apt-get update && \
-    apt-get install -y ca-certificates && \
-    apt-get clean && rm -rf /var/lib/apt/lists/*
-COPY --from=build-arm64 /go/src/github.com/ollama/ollama/dist/linux-arm64/bin/ /bin/
-COPY --from=build-arm64 /go/src/github.com/ollama/ollama/dist/linux-arm64/lib/ /lib/
-COPY --from=runners-jetpack5-arm64 /go/src/github.com/ollama/ollama/dist/linux-arm64-jetpack5/lib/ /lib/
-COPY --from=runners-jetpack6-arm64 /go/src/github.com/ollama/ollama/dist/linux-arm64-jetpack6/lib/ /lib/
+FROM --platform=linux/arm64 scratch AS rocm
+COPY --from=rocm-6 dist/lib/ollama/rocm /lib/ollama/rocm

+FROM ${FLAVOR} AS archive
+COPY --from=cpu dist/lib/ollama /lib/ollama
+COPY --from=build /bin/ollama /bin/ollama

-# ROCm libraries larger so we keep it distinct from the CPU/CUDA image
-FROM --platform=linux/amd64 ubuntu:22.04 AS runtime-rocm
-# Frontload the rocm libraries which are large, and rarely change to increase chance of a common layer
-# across releases
-COPY --from=build-amd64 /go/src/github.com/ollama/ollama/dist/linux-amd64-rocm/lib/ /lib/
-RUN apt-get update && \
-    apt-get install -y ca-certificates && \
-    apt-get clean && rm -rf /var/lib/apt/lists/*
-COPY --from=build-amd64 /go/src/github.com/ollama/ollama/dist/linux-amd64/bin/ /bin/
-COPY --from=runners-rocm-amd64 /go/src/github.com/ollama/ollama/dist/linux-amd64/lib/ /lib/
-
-EXPOSE 11434
-ENV OLLAMA_HOST 0.0.0.0
-
-ENTRYPOINT ["/bin/ollama"]
-CMD ["serve"]
-
-FROM runtime-$TARGETARCH
-EXPOSE 11434
-ENV OLLAMA_HOST 0.0.0.0
+FROM ubuntu:20.04
+RUN apt-get update \
+    && apt-get install -y ca-certificates \
+    && apt-get clean \
+    && rm -rf /var/lib/apt/lists/*
+COPY --from=archive /bin /usr/bin
 ENV PATH=/usr/local/sbin:/usr/local/bin:/usr/sbin:/usr/bin:/sbin:/bin
+COPY --from=archive /lib/ollama /usr/lib/ollama
 ENV LD_LIBRARY_PATH=/usr/local/nvidia/lib:/usr/local/nvidia/lib64
 ENV NVIDIA_DRIVER_CAPABILITIES=compute,utility
 ENV NVIDIA_VISIBLE_DEVICES=all
-
+ENV OLLAMA_HOST=0.0.0.0:11434
+EXPOSE 11434
 ENTRYPOINT ["/bin/ollama"]
 CMD ["serve"]