Skip to content

GitLab

Commit da72235e authored by Daniel Hiltgen's avatar Daniel Hiltgen
Browse files

Combine the 2 Dockerfiles and add ROCm 

This renames Dockerfile.build to Dockerfile, and adds some new stages
to support 2 modes of building - the build_linux.sh script uses
intermediate stages to extract the artifacts for ./dist, and the default
build generates a container image usable by both cuda and rocm cards.
This required transitioniing the x86 base to the rocm image to avoid
layer bloat.
parent 89c4aee2
Hide whitespace changes
Inline Side-by-side
Showing with 111 additions and 116 deletions
Dockerfile
View file @ da72235e
FROM nvidia/cuda:11.8.0-devel-ubuntu22.04 ARG GOLANG_VERSION=1.21.3
ARG CMAKE_VERSION=3.22.1
ARG CUDA_VERSION=11.3.1
ARG TARGETARCH # Copy the minimal context we need to run the generate scripts
ARG GOFLAGS="'-ldflags=-w -s'" FROM scratch AS llm-code
COPY .git .git
COPY .gitmodules .gitmodules
COPY llm llm
FROM --platform=linux/amd64 nvidia/cuda:$CUDA_VERSION-devel-centos7 AS cuda-build-amd64
ARG CMAKE_VERSION
ARG CGO_CFLAGS
COPY ./scripts/rh_linux_deps.sh /
RUN CMAKE_VERSION=${CMAKE_VERSION} sh /rh_linux_deps.sh
ENV PATH /opt/rh/devtoolset-10/root/usr/bin:$PATH
COPY --from=llm-code / /go/src/github.com/jmorganca/ollama/
WORKDIR /go/src/github.com/jmorganca/ollama/llm/generate
RUN OLLAMA_SKIP_CPU_GENERATE=1 sh gen_linux.sh
FROM --platform=linux/arm64 nvidia/cuda:$CUDA_VERSION-devel-rockylinux8 AS cuda-build-arm64
ARG CMAKE_VERSION
ARG CGO_CFLAGS
COPY ./scripts/rh_linux_deps.sh /
RUN CMAKE_VERSION=${CMAKE_VERSION} sh /rh_linux_deps.sh
ENV PATH /opt/rh/gcc-toolset-10/root/usr/bin:$PATH
COPY --from=llm-code / /go/src/github.com/jmorganca/ollama/
WORKDIR /go/src/github.com/jmorganca/ollama/llm/generate
RUN OLLAMA_SKIP_CPU_GENERATE=1 sh gen_linux.sh
FROM --platform=linux/amd64 rocm/dev-centos-7:5.7.1-complete AS rocm-5-build-amd64
ARG CMAKE_VERSION
ARG CGO_CFLAGS
COPY ./scripts/rh_linux_deps.sh /
RUN CMAKE_VERSION=${CMAKE_VERSION} sh /rh_linux_deps.sh
ENV PATH /opt/rh/devtoolset-10/root/usr/bin:$PATH
ENV LIBRARY_PATH /opt/amdgpu/lib64
COPY --from=llm-code / /go/src/github.com/jmorganca/ollama/
WORKDIR /go/src/github.com/jmorganca/ollama/llm/generate
RUN OLLAMA_SKIP_CPU_GENERATE=1 sh gen_linux.sh
FROM --platform=linux/amd64 rocm/dev-centos-7:6.0-complete AS rocm-6-build-amd64
ARG CMAKE_VERSION
ARG CGO_CFLAGS
COPY ./scripts/rh_linux_deps.sh /
RUN CMAKE_VERSION=${CMAKE_VERSION} sh /rh_linux_deps.sh
ENV PATH /opt/rh/devtoolset-10/root/usr/bin:$PATH
ENV LIBRARY_PATH /opt/amdgpu/lib64
COPY --from=llm-code / /go/src/github.com/jmorganca/ollama/
WORKDIR /go/src/github.com/jmorganca/ollama/llm/generate
RUN OLLAMA_SKIP_CPU_GENERATE=1 sh gen_linux.sh
FROM --platform=linux/amd64 centos:7 AS cpu-build-amd64
ARG CMAKE_VERSION
ARG GOLANG_VERSION
ARG OLLAMA_CUSTOM_CPU_DEFS
ARG CGO_CFLAGS
COPY ./scripts/rh_linux_deps.sh /
RUN CMAKE_VERSION=${CMAKE_VERSION} GOLANG_VERSION=${GOLANG_VERSION} sh /rh_linux_deps.sh
ENV PATH /opt/rh/devtoolset-10/root/usr/bin:$PATH
COPY --from=llm-code / /go/src/github.com/jmorganca/ollama/
WORKDIR /go/src/github.com/jmorganca/ollama/llm/generate
RUN sh gen_linux.sh
FROM --platform=linux/arm64 centos:7 AS cpu-build-arm64
ARG CMAKE_VERSION
ARG GOLANG_VERSION
ARG OLLAMA_CUSTOM_CPU_DEFS
ARG CGO_CFLAGS
COPY ./scripts/rh_linux_deps.sh /
RUN CMAKE_VERSION=${CMAKE_VERSION} GOLANG_VERSION=${GOLANG_VERSION} sh /rh_linux_deps.sh
ENV PATH /opt/rh/devtoolset-10/root/usr/bin:$PATH
COPY --from=llm-code / /go/src/github.com/jmorganca/ollama/
WORKDIR /go/src/github.com/jmorganca/ollama/llm/generate
RUN sh gen_linux.sh
# Intermediate stage used for ./scripts/build_linux.sh
FROM --platform=linux/amd64 cpu-build-amd64 AS build-amd64
ENV CGO_ENABLED 1
ARG GOFLAGS
ARG CGO_CFLAGS
WORKDIR /go/src/github.com/jmorganca/ollama WORKDIR /go/src/github.com/jmorganca/ollama
RUN apt-get update && apt-get install -y git build-essential cmake COPY . .
ADD https://dl.google.com/go/go1.21.3.linux-$TARGETARCH.tar.gz /tmp/go1.21.3.tar.gz COPY --from=cuda-build-amd64 /go/src/github.com/jmorganca/ollama/llm/llama.cpp/build/linux/ llm/llama.cpp/build/linux/
RUN mkdir -p /usr/local && tar xz -C /usr/local </tmp/go1.21.3.tar.gz COPY --from=rocm-5-build-amd64 /go/src/github.com/jmorganca/ollama/llm/llama.cpp/build/linux/ llm/llama.cpp/build/linux/
COPY --from=rocm-6-build-amd64 /go/src/github.com/jmorganca/ollama/llm/llama.cpp/build/linux/ llm/llama.cpp/build/linux/
RUN go build .
# Intermediate stage used for ./scripts/build_linux.sh
FROM --platform=linux/arm64 cpu-build-arm64 AS build-arm64
ENV CGO_ENABLED 1
ARG GOLANG_VERSION
ARG GOFLAGS
ARG CGO_CFLAGS
WORKDIR /go/src/github.com/jmorganca/ollama
COPY . . COPY . .
ENV GOARCH=$TARGETARCH COPY --from=cuda-build-arm64 /go/src/github.com/jmorganca/ollama/llm/llama.cpp/build/linux/ llm/llama.cpp/build/linux/
ENV GOFLAGS=$GOFLAGS RUN go build .
RUN /usr/local/go/bin/go generate ./... \
&& /usr/local/go/bin/go build .
FROM ubuntu:22.04 # Runtime stages
FROM --platform=linux/amd64 rocm/dev-centos-7:6.0-complete as runtime-amd64
COPY --from=build-amd64 /go/src/github.com/jmorganca/ollama/ollama /bin/ollama
FROM --platform=linux/arm64 ubuntu:22.04 as runtime-arm64
RUN apt-get update && apt-get install -y ca-certificates RUN apt-get update && apt-get install -y ca-certificates
COPY --from=0 /go/src/github.com/jmorganca/ollama/ollama /bin/ollama COPY --from=build-arm64 /go/src/github.com/jmorganca/ollama/ollama /bin/ollama
FROM runtime-$TARGETARCH
EXPOSE 11434 EXPOSE 11434
ENV OLLAMA_HOST 0.0.0.0 ENV OLLAMA_HOST 0.0.0.0
ENV PATH=/usr/local/sbin:/usr/local/bin:/usr/sbin:/usr/bin:/sbin:/bin
# set some environment variable for better NVIDIA compatibility ENV LD_LIBRARY_PATH=/usr/local/nvidia/lib:/usr/local/nvidia/lib64:/opt/rocm/lib:
ENV PATH=/usr/local/nvidia/bin:/usr/local/cuda/bin:/usr/local/sbin:/usr/local/bin:/usr/sbin:/usr/bin:/sbin:/bin
ENV LD_LIBRARY_PATH=/usr/local/nvidia/lib:/usr/local/nvidia/lib64
ENV NVIDIA_DRIVER_CAPABILITIES=compute,utility ENV NVIDIA_DRIVER_CAPABILITIES=compute,utility
ENTRYPOINT ["/bin/ollama"] ENTRYPOINT ["/bin/ollama"]
......
Dockerfile.build deleted 100644 → 0
View file @ 89c4aee2
ARG GOLANG_VERSION=1.21.3
ARG CMAKE_VERSION=3.22.1
ARG CUDA_VERSION=11.3.1
# Copy the minimal context we need to run the generate scripts
FROM scratch AS llm-code
COPY .git .git
COPY .gitmodules .gitmodules
COPY llm llm
FROM --platform=linux/amd64 nvidia/cuda:$CUDA_VERSION-devel-centos7 AS cuda-build-amd64
ARG CMAKE_VERSION
ARG CGO_CFLAGS
COPY ./scripts/rh_linux_deps.sh /
RUN CMAKE_VERSION=${CMAKE_VERSION} sh /rh_linux_deps.sh
ENV PATH /opt/rh/devtoolset-10/root/usr/bin:$PATH
COPY --from=llm-code / /go/src/github.com/jmorganca/ollama/
WORKDIR /go/src/github.com/jmorganca/ollama/llm/generate
RUN OLLAMA_SKIP_CPU_GENERATE=1 sh gen_linux.sh
FROM --platform=linux/arm64 nvidia/cuda:$CUDA_VERSION-devel-rockylinux8 AS cuda-build-arm64
ARG CMAKE_VERSION
ARG CGO_CFLAGS
COPY ./scripts/rh_linux_deps.sh /
RUN CMAKE_VERSION=${CMAKE_VERSION} sh /rh_linux_deps.sh
ENV PATH /opt/rh/gcc-toolset-10/root/usr/bin:$PATH
COPY --from=llm-code / /go/src/github.com/jmorganca/ollama/
WORKDIR /go/src/github.com/jmorganca/ollama/llm/generate
RUN OLLAMA_SKIP_CPU_GENERATE=1 sh gen_linux.sh
FROM --platform=linux/amd64 rocm/dev-centos-7:5.7.1-complete AS rocm-5-build-amd64
ARG CMAKE_VERSION
ARG CGO_CFLAGS
COPY ./scripts/rh_linux_deps.sh /
RUN CMAKE_VERSION=${CMAKE_VERSION} sh /rh_linux_deps.sh
ENV PATH /opt/rh/devtoolset-10/root/usr/bin:$PATH
ENV LIBRARY_PATH /opt/amdgpu/lib64
COPY --from=llm-code / /go/src/github.com/jmorganca/ollama/
WORKDIR /go/src/github.com/jmorganca/ollama/llm/generate
RUN OLLAMA_SKIP_CPU_GENERATE=1 sh gen_linux.sh
FROM --platform=linux/amd64 rocm/dev-centos-7:6.0-complete AS rocm-6-build-amd64
ARG CMAKE_VERSION
ARG CGO_CFLAGS
COPY ./scripts/rh_linux_deps.sh /
RUN CMAKE_VERSION=${CMAKE_VERSION} sh /rh_linux_deps.sh
ENV PATH /opt/rh/devtoolset-10/root/usr/bin:$PATH
ENV LIBRARY_PATH /opt/amdgpu/lib64
COPY --from=llm-code / /go/src/github.com/jmorganca/ollama/
WORKDIR /go/src/github.com/jmorganca/ollama/llm/generate
RUN OLLAMA_SKIP_CPU_GENERATE=1 sh gen_linux.sh
FROM --platform=linux/amd64 centos:7 AS cpu-build-amd64
ARG CMAKE_VERSION
ARG GOLANG_VERSION
ARG OLLAMA_CUSTOM_CPU_DEFS
ARG CGO_CFLAGS
COPY ./scripts/rh_linux_deps.sh /
RUN CMAKE_VERSION=${CMAKE_VERSION} GOLANG_VERSION=${GOLANG_VERSION} sh /rh_linux_deps.sh
ENV PATH /opt/rh/devtoolset-10/root/usr/bin:$PATH
COPY --from=llm-code / /go/src/github.com/jmorganca/ollama/
WORKDIR /go/src/github.com/jmorganca/ollama/llm/generate
RUN sh gen_linux.sh
FROM --platform=linux/arm64 centos:7 AS cpu-build-arm64
ARG CMAKE_VERSION
ARG GOLANG_VERSION
ARG OLLAMA_CUSTOM_CPU_DEFS
ARG CGO_CFLAGS
COPY ./scripts/rh_linux_deps.sh /
RUN CMAKE_VERSION=${CMAKE_VERSION} GOLANG_VERSION=${GOLANG_VERSION} sh /rh_linux_deps.sh
ENV PATH /opt/rh/devtoolset-10/root/usr/bin:$PATH
COPY --from=llm-code / /go/src/github.com/jmorganca/ollama/
WORKDIR /go/src/github.com/jmorganca/ollama/llm/generate
RUN sh gen_linux.sh
FROM --platform=linux/amd64 cpu-build-amd64 AS build-amd64
ENV CGO_ENABLED 1
ARG GOFLAGS
ARG CGO_CFLAGS
WORKDIR /go/src/github.com/jmorganca/ollama
COPY . .
COPY --from=cuda-build-amd64 /go/src/github.com/jmorganca/ollama/llm/llama.cpp/build/linux/ llm/llama.cpp/build/linux/
COPY --from=rocm-5-build-amd64 /go/src/github.com/jmorganca/ollama/llm/llama.cpp/build/linux/ llm/llama.cpp/build/linux/
COPY --from=rocm-6-build-amd64 /go/src/github.com/jmorganca/ollama/llm/llama.cpp/build/linux/ llm/llama.cpp/build/linux/
RUN go build .
FROM --platform=linux/arm64 cpu-build-arm64 AS build-arm64
ENV CGO_ENABLED 1
ARG GOLANG_VERSION
ARG GOFLAGS
ARG CGO_CFLAGS
WORKDIR /go/src/github.com/jmorganca/ollama
COPY . .
COPY --from=cuda-build-arm64 /go/src/github.com/jmorganca/ollama/llm/llama.cpp/build/linux/ llm/llama.cpp/build/linux/
RUN go build .
FROM build-$TARGETARCH
scripts/build_linux.sh
View file @ da72235e
...@@ -9,7 +9,15 @@ BUILD_ARCH=${BUILD_ARCH:-"amd64 arm64"} ...@@ -9,7 +9,15 @@ BUILD_ARCH=${BUILD_ARCH:-"amd64 arm64"}
mkdir -p dist mkdir -p dist
for TARGETARCH in ${BUILD_ARCH}; do for TARGETARCH in ${BUILD_ARCH}; do
docker build --platform=linux/$TARGETARCH --build-arg=GOFLAGS --build-arg=CGO_CFLAGS --build-arg=OLLAMA_CUSTOM_CPU_DEFS -f Dockerfile.build -t builder:$TARGETARCH . docker build \
--platform=linux/$TARGETARCH \
--build-arg=GOFLAGS \
--build-arg=CGO_CFLAGS \
--build-arg=OLLAMA_CUSTOM_CPU_DEFS \
--target build-$TARGETARCH \
-f Dockerfile \
-t builder:$TARGETARCH \
.
docker create --platform linux/$TARGETARCH --name builder-$TARGETARCH builder:$TARGETARCH docker create --platform linux/$TARGETARCH --name builder-$TARGETARCH builder:$TARGETARCH
docker cp builder-$TARGETARCH:/go/src/github.com/jmorganca/ollama/ollama ./dist/ollama-linux-$TARGETARCH docker cp builder-$TARGETARCH:/go/src/github.com/jmorganca/ollama/ollama ./dist/ollama-linux-$TARGETARCH
docker rm builder-$TARGETARCH docker rm builder-$TARGETARCH
......
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment