baalajimaestro/ollama
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity
ollama/Dockerfile
Daniel Hiltgen 6c5ccb11f9 Revamp ROCm support 
This refines where we extract the LLM libraries to by adding a new
OLLAMA_HOME env var, that defaults to `~/.ollama` The logic was already
idempotenent, so this should speed up startups after the first time a
new release is deployed.  It also cleans up after itself.

We now build only a single ROCm version (latest major) on both windows
and linux.  Given the large size of ROCms tensor files, we split the
dependency out.  It's bundled into the installer on windows, and a
separate download on windows.  The linux install script is now smart and
detects the presence of AMD GPUs and looks to see if rocm v6 is already
present, and if not, then downloads our dependency tar file.

For Linux discovery, we now use sysfs and check each GPU against what
ROCm supports so we can degrade to CPU gracefully instead of having
llama.cpp+rocm assert/crash on us.  For Windows, we now use go's windows
dynamic library loading logic to access the amdhip64.dll APIs to query
the GPU information.
2024-03-07 10:36:50 -08:00

135 lines
5.5 KiB
Docker
Raw Blame History

ARG GOLANG_VERSION=1.22.1
ARG CMAKE_VERSION=3.22.1
ARG CUDA_VERSION=11.3.1
ARG ROCM_VERSION=6.0
# 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:${ROCM_VERSION}-complete AS rocm-build-amd64
ARG CMAKE_VERSION
COPY ./scripts/rh_linux_deps.sh /
RUN CMAKE_VERSION=${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
RUN mkdir /tmp/scratch && \
for dep in $(cat /go/src/github.com/jmorganca/ollama/llm/llama.cpp/build/linux/x86_64/rocm*/lib/deps.txt) ; do \
cp ${dep} /tmp/scratch/ || exit 1 ; \
done && \
(cd /opt/rocm/lib && tar cf - rocblas/library) | (cd /tmp/scratch/ && tar xf - ) && \
mkdir -p /go/src/github.com/jmorganca/ollama/dist/deps/ && \
(cd /tmp/scratch/ && tar czvf /go/src/github.com/jmorganca/ollama/dist/deps/rocm-amd64-deps.tgz . )
FROM --platform=linux/amd64 centos:7 AS cpu-builder-amd64
ARG CMAKE_VERSION
ARG GOLANG_VERSION
COPY ./scripts/rh_linux_deps.sh /
RUN CMAKE_VERSION=${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:$PATH
COPY --from=llm-code / /go/src/github.com/jmorganca/ollama/
WORKDIR /go/src/github.com/jmorganca/ollama/llm/generate
# Note, we only build the "base" CPU variant on arm since avx/avx2 are x86 features
ARG OLLAMA_CUSTOM_CPU_DEFS
ARG CGO_CFLAGS
RUN OLLAMA_CPU_TARGET="cpu" sh gen_linux.sh
# Intermediate stage used for ./scripts/build_linux.sh
FROM --platform=linux/amd64 cpu-build-amd64 AS build-amd64
ENV CGO_ENABLED 1
WORKDIR /go/src/github.com/jmorganca/ollama
COPY . .
COPY --from=cpu_avx-build-amd64 /go/src/github.com/jmorganca/ollama/llm/llama.cpp/build/linux/ llm/llama.cpp/build/linux/
COPY --from=cpu_avx2-build-amd64 /go/src/github.com/jmorganca/ollama/llm/llama.cpp/build/linux/ llm/llama.cpp/build/linux/
COPY --from=cuda-build-amd64 /go/src/github.com/jmorganca/ollama/llm/llama.cpp/build/linux/ llm/llama.cpp/build/linux/
COPY --from=rocm-build-amd64 /go/src/github.com/jmorganca/ollama/llm/llama.cpp/build/linux/ llm/llama.cpp/build/linux/
COPY --from=rocm-build-amd64 /go/src/github.com/jmorganca/ollama/dist/deps/ ./dist/deps/
ARG GOFLAGS
ARG CGO_CFLAGS
RUN go build .
# Intermediate stage used for ./scripts/build_linux.sh
FROM --platform=linux/arm64 cpu-build-arm64 AS build-arm64
ENV CGO_ENABLED 1
ARG GOLANG_VERSION
WORKDIR /go/src/github.com/jmorganca/ollama
COPY . .
COPY --from=cuda-build-arm64 /go/src/github.com/jmorganca/ollama/llm/llama.cpp/build/linux/ llm/llama.cpp/build/linux/
ARG GOFLAGS
ARG CGO_CFLAGS
RUN go build .
# Runtime stages
FROM --platform=linux/amd64 ubuntu:22.04 as runtime-amd64
RUN apt-get update && apt-get install -y ca-certificates
COPY --from=build-amd64 /go/src/github.com/jmorganca/ollama/ollama /bin/ollama
FROM --platform=linux/arm64 ubuntu:22.04 as runtime-arm64
RUN apt-get update && apt-get install -y ca-certificates
COPY --from=build-arm64 /go/src/github.com/jmorganca/ollama/ollama /bin/ollama
# Radeon images are much larger so we keep it distinct from the CPU/CUDA image
FROM --platform=linux/amd64 rocm/dev-centos-7:${ROCM_VERSION}-complete as runtime-rocm
RUN update-pciids
COPY --from=build-amd64 /go/src/github.com/jmorganca/ollama/ollama /bin/ollama
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
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
ENV NVIDIA_DRIVER_CAPABILITIES=compute,utility
ENV NVIDIA_VISIBLE_DEVICES=all
ENTRYPOINT ["/bin/ollama"]
CMD ["serve"]
Reference in a new issue View git blame Copy permalink