ollama/Dockerfile
Daniel Hiltgen df54c723ae Make CPU builds parallel and customizable AMD GPUs
The linux build now support parallel CPU builds to speed things up.
This also exposes AMD GPU targets as an optional setting for advaced
users who want to alter our default set.
2024-01-21 15:12:21 -08:00

126 lines
5.1 KiB
Docker

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:$CUDA_VERSION-devel-centos7 AS cuda-build-amd64
ARG CMAKE_VERSION
COPY ./scripts/rh_linux_deps.sh /
RUN CMAKE_VERSION=${CMAKE_VERSION} sh /rh_linux_deps.sh
ENV PATH /opt/rh/devtoolset-10/root/usr/bin:$PATH
COPY --from=llm-code / /go/src/github.com/jmorganca/ollama/
WORKDIR /go/src/github.com/jmorganca/ollama/llm/generate
ARG CGO_CFLAGS
RUN OLLAMA_SKIP_CPU_GENERATE=1 sh gen_linux.sh
FROM --platform=linux/arm64 nvidia/cuda:$CUDA_VERSION-devel-rockylinux8 AS cuda-build-arm64
ARG CMAKE_VERSION
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
ARG CGO_CFLAGS
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
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
ARG CGO_CFLAGS
ARG AMDGPU_TARGETS
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
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
ARG CGO_CFLAGS
ARG AMDGPU_TARGETS
RUN OLLAMA_SKIP_CPU_GENERATE=1 sh gen_linux.sh
FROM --platform=linux/amd64 centos:7 AS cpu-builder-amd64
ARG CMAKE_VERSION
ARG GOLANG_VERSION
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:$PATH
COPY --from=llm-code / /go/src/github.com/jmorganca/ollama/
ARG OLLAMA_CUSTOM_CPU_DEFS
ARG CGO_CFLAGS
WORKDIR /go/src/github.com/jmorganca/ollama/llm/generate
FROM --platform=linux/amd64 cpu-builder-amd64 AS cpu-build-amd64
RUN OLLAMA_CPU_TARGET="cpu" sh gen_linux.sh
FROM --platform=linux/amd64 cpu-builder-amd64 AS cpu_avx-build-amd64
RUN OLLAMA_CPU_TARGET="cpu_avx" sh gen_linux.sh
FROM --platform=linux/amd64 cpu-builder-amd64 AS cpu_avx2-build-amd64
RUN OLLAMA_CPU_TARGET="cpu_avx2" sh gen_linux.sh
FROM --platform=linux/arm64 centos:7 AS cpu-build-arm64
ARG CMAKE_VERSION
ARG GOLANG_VERSION
COPY ./scripts/rh_linux_deps.sh /
RUN CMAKE_VERSION=${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
# Note, we only build the "base" CPU variant on arm since avx/avx2 are x86 features
ARG OLLAMA_CUSTOM_CPU_DEFS
ARG CGO_CFLAGS
RUN OLLAMA_CPU_TARGET="cpu" 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
WORKDIR /go/src/github.com/jmorganca/ollama
COPY . .
COPY --from=cpu_avx-build-amd64 /go/src/github.com/jmorganca/ollama/llm/llama.cpp/build/linux/ llm/llama.cpp/build/linux/
COPY --from=cpu_avx2-build-amd64 /go/src/github.com/jmorganca/ollama/llm/llama.cpp/build/linux/ llm/llama.cpp/build/linux/
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/
ARG GOFLAGS
ARG CGO_CFLAGS
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
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/
ARG GOFLAGS
ARG CGO_CFLAGS
RUN go build .
# 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
COPY --from=build-arm64 /go/src/github.com/jmorganca/ollama/ollama /bin/ollama
FROM runtime-$TARGETARCH
EXPOSE 11434
ENV OLLAMA_HOST 0.0.0.0
ENV PATH=/usr/local/sbin:/usr/local/bin:/usr/sbin:/usr/bin:/sbin:/bin
ENV LD_LIBRARY_PATH=/usr/local/nvidia/lib:/usr/local/nvidia/lib64:/opt/rocm/lib:
ENV NVIDIA_DRIVER_CAPABILITIES=compute,utility
ENTRYPOINT ["/bin/ollama"]
CMD ["serve"]