baalajimaestro/ollama
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity
ollama/Dockerfile.build

100 lines
3.7 KiB
Text
Raw Normal View History

Build linux using ubuntu 20.04 This changes the container-based linux build to use an older Ubuntu distro to improve our compatibility matrix for older user machines
2023-12-18 20:05:59 +00:00
ARG GOLANG_VERSION=1.21.3
update build
2024-01-04 21:25:38 +00:00
ARG CMAKE_VERSION=3.22.1
ARG CUDA_VERSION=11.3.1
DRY out the Dockefile.build
2024-01-07 00:46:55 +00:00
# Copy the minimal context we need to run the generate scripts
FROM scratch AS llm-code
Support multiple variants for a given llm lib type In some cases we may want multiple variants for a given GPU type or CPU. This adds logic to have an optional Variant which we can use to select an optimal library, but also allows us to try multiple variants in case some fail to load. This can be useful for scenarios such as ROCm v5 vs v6 incompatibility or potentially CPU features.
2024-01-05 20:13:08 +00:00
COPY .git .git
COPY .gitmodules .gitmodules
COPY llm llm
update `Dockerfile` to pass `GOFLAGS`
2023-10-03 14:05:09 +00:00
DRY out the Dockefile.build
2024-01-07 00:46:55 +00:00
FROM --platform=linux/amd64 nvidia/cuda:$CUDA_VERSION-devel-centos7 AS cuda-build-amd64
ARG CMAKE_VERSION
Add multiple CPU variants for Intel Mac This also refines the build process for the ext_server build.
2024-01-13 00:28:00 +00:00
ARG CGO_CFLAGS
DRY out the Dockefile.build
2024-01-07 00:46:55 +00:00
COPY ./scripts/rh_linux_deps.sh /
RUN CMAKE_VERSION=${CMAKE_VERSION} sh /rh_linux_deps.sh
ENV PATH /opt/rh/devtoolset-10/root/usr/bin:$PATH
COPY --from=llm-code / /go/src/github.com/jmorganca/ollama/
Support multiple variants for a given llm lib type In some cases we may want multiple variants for a given GPU type or CPU. This adds logic to have an optional Variant which we can use to select an optimal library, but also allows us to try multiple variants in case some fail to load. This can be useful for scenarios such as ROCm v5 vs v6 incompatibility or potentially CPU features.
2024-01-05 20:13:08 +00:00
WORKDIR /go/src/github.com/jmorganca/ollama/llm/generate
DRY out the Dockefile.build
2024-01-07 00:46:55 +00:00
RUN OLLAMA_SKIP_CPU_GENERATE=1 sh gen_linux.sh
update build
2024-01-04 21:25:38 +00:00
FROM --platform=linux/arm64 nvidia/cuda:$CUDA_VERSION-devel-rockylinux8 AS cuda-build-arm64
ARG CMAKE_VERSION
Add multiple CPU variants for Intel Mac This also refines the build process for the ext_server build.
2024-01-13 00:28:00 +00:00
ARG CGO_CFLAGS
DRY out the Dockefile.build
2024-01-07 00:46:55 +00:00
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/
Support multiple variants for a given llm lib type In some cases we may want multiple variants for a given GPU type or CPU. This adds logic to have an optional Variant which we can use to select an optimal library, but also allows us to try multiple variants in case some fail to load. This can be useful for scenarios such as ROCm v5 vs v6 incompatibility or potentially CPU features.
2024-01-05 20:13:08 +00:00
WORKDIR /go/src/github.com/jmorganca/ollama/llm/generate
DRY out the Dockefile.build
2024-01-07 00:46:55 +00:00
RUN OLLAMA_SKIP_CPU_GENERATE=1 sh gen_linux.sh
update build
2024-01-04 21:25:38 +00:00
Support multiple variants for a given llm lib type In some cases we may want multiple variants for a given GPU type or CPU. This adds logic to have an optional Variant which we can use to select an optimal library, but also allows us to try multiple variants in case some fail to load. This can be useful for scenarios such as ROCm v5 vs v6 incompatibility or potentially CPU features.
2024-01-05 20:13:08 +00:00
FROM --platform=linux/amd64 rocm/dev-centos-7:5.7.1-complete AS rocm-5-build-amd64
update build
2024-01-04 21:25:38 +00:00
ARG CMAKE_VERSION
Add multiple CPU variants for Intel Mac This also refines the build process for the ext_server build.
2024-01-13 00:28:00 +00:00
ARG CGO_CFLAGS
DRY out the Dockefile.build
2024-01-07 00:46:55 +00:00
COPY ./scripts/rh_linux_deps.sh /
RUN CMAKE_VERSION=${CMAKE_VERSION} sh /rh_linux_deps.sh
update build
2024-01-04 21:25:38 +00:00
ENV PATH /opt/rh/devtoolset-10/root/usr/bin:$PATH
ENV LIBRARY_PATH /opt/amdgpu/lib64
DRY out the Dockefile.build
2024-01-07 00:46:55 +00:00
COPY --from=llm-code / /go/src/github.com/jmorganca/ollama/
Support multiple variants for a given llm lib type In some cases we may want multiple variants for a given GPU type or CPU. This adds logic to have an optional Variant which we can use to select an optimal library, but also allows us to try multiple variants in case some fail to load. This can be useful for scenarios such as ROCm v5 vs v6 incompatibility or potentially CPU features.
2024-01-05 20:13:08 +00:00
WORKDIR /go/src/github.com/jmorganca/ollama/llm/generate
RUN OLLAMA_SKIP_CPU_GENERATE=1 sh gen_linux.sh
update build
2024-01-04 21:25:38 +00:00
Support multiple variants for a given llm lib type In some cases we may want multiple variants for a given GPU type or CPU. This adds logic to have an optional Variant which we can use to select an optimal library, but also allows us to try multiple variants in case some fail to load. This can be useful for scenarios such as ROCm v5 vs v6 incompatibility or potentially CPU features.
2024-01-05 20:13:08 +00:00
FROM --platform=linux/amd64 rocm/dev-centos-7:6.0-complete AS rocm-6-build-amd64
ARG CMAKE_VERSION
Add multiple CPU variants for Intel Mac This also refines the build process for the ext_server build.
2024-01-13 00:28:00 +00:00
ARG CGO_CFLAGS
DRY out the Dockefile.build
2024-01-07 00:46:55 +00:00
COPY ./scripts/rh_linux_deps.sh /
RUN CMAKE_VERSION=${CMAKE_VERSION} sh /rh_linux_deps.sh
Support multiple variants for a given llm lib type In some cases we may want multiple variants for a given GPU type or CPU. This adds logic to have an optional Variant which we can use to select an optimal library, but also allows us to try multiple variants in case some fail to load. This can be useful for scenarios such as ROCm v5 vs v6 incompatibility or potentially CPU features.
2024-01-05 20:13:08 +00:00
ENV PATH /opt/rh/devtoolset-10/root/usr/bin:$PATH
ENV LIBRARY_PATH /opt/amdgpu/lib64
DRY out the Dockefile.build
2024-01-07 00:46:55 +00:00
COPY --from=llm-code / /go/src/github.com/jmorganca/ollama/
Support multiple variants for a given llm lib type In some cases we may want multiple variants for a given GPU type or CPU. This adds logic to have an optional Variant which we can use to select an optimal library, but also allows us to try multiple variants in case some fail to load. This can be useful for scenarios such as ROCm v5 vs v6 incompatibility or potentially CPU features.
2024-01-05 20:13:08 +00:00
WORKDIR /go/src/github.com/jmorganca/ollama/llm/generate
RUN OLLAMA_SKIP_CPU_GENERATE=1 sh gen_linux.sh
update build
2024-01-04 21:25:38 +00:00
DRY out the Dockefile.build
2024-01-07 00:46:55 +00:00
FROM --platform=linux/amd64 centos:7 AS cpu-build-amd64
ARG CMAKE_VERSION
update build
2024-01-04 21:25:38 +00:00
ARG GOLANG_VERSION
Build multiple CPU variants and pick the best This reduces the built-in linux version to not use any vector extensions which enables the resulting builds to run under Rosetta on MacOS in Docker. Then at runtime it checks for the actual CPU vector extensions and loads the best CPU library available
2024-01-07 23:48:05 +00:00
ARG OLLAMA_CUSTOM_CPU_DEFS
Add multiple CPU variants for Intel Mac This also refines the build process for the ext_server build.
2024-01-13 00:28:00 +00:00
ARG CGO_CFLAGS
DRY out the Dockefile.build
2024-01-07 00:46:55 +00:00
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:$PATH
COPY --from=llm-code / /go/src/github.com/jmorganca/ollama/
WORKDIR /go/src/github.com/jmorganca/ollama/llm/generate
RUN sh gen_linux.sh
update build
2024-01-04 21:25:38 +00:00
DRY out the Dockefile.build
2024-01-07 00:46:55 +00:00
FROM --platform=linux/arm64 centos:7 AS cpu-build-arm64
ARG CMAKE_VERSION
ARG GOLANG_VERSION
Build multiple CPU variants and pick the best This reduces the built-in linux version to not use any vector extensions which enables the resulting builds to run under Rosetta on MacOS in Docker. Then at runtime it checks for the actual CPU vector extensions and loads the best CPU library available
2024-01-07 23:48:05 +00:00
ARG OLLAMA_CUSTOM_CPU_DEFS
Add multiple CPU variants for Intel Mac This also refines the build process for the ext_server build.
2024-01-13 00:28:00 +00:00
ARG CGO_CFLAGS
DRY out the Dockefile.build
2024-01-07 00:46:55 +00:00
COPY ./scripts/rh_linux_deps.sh /
RUN CMAKE_VERSION=${CMAKE_VERSION} GOLANG_VERSION=${GOLANG_VERSION} sh /rh_linux_deps.sh
update build
2024-01-04 21:25:38 +00:00
ENV PATH /opt/rh/devtoolset-10/root/usr/bin:$PATH
DRY out the Dockefile.build
2024-01-07 00:46:55 +00:00
COPY --from=llm-code / /go/src/github.com/jmorganca/ollama/
WORKDIR /go/src/github.com/jmorganca/ollama/llm/generate
RUN sh gen_linux.sh
update build
2024-01-04 21:25:38 +00:00
DRY out the Dockefile.build
2024-01-07 00:46:55 +00:00
FROM --platform=linux/amd64 cpu-build-amd64 AS build-amd64
ENV CGO_ENABLED 1
ARG GOFLAGS
Add multiple CPU variants for Intel Mac This also refines the build process for the ext_server build.
2024-01-13 00:28:00 +00:00
ARG CGO_CFLAGS
update build
2024-01-04 21:25:38 +00:00
WORKDIR /go/src/github.com/jmorganca/ollama
COPY . .
Support multiple variants for a given llm lib type In some cases we may want multiple variants for a given GPU type or CPU. This adds logic to have an optional Variant which we can use to select an optimal library, but also allows us to try multiple variants in case some fail to load. This can be useful for scenarios such as ROCm v5 vs v6 incompatibility or potentially CPU features.
2024-01-05 20:13:08 +00:00
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/
update build
2024-01-04 21:25:38 +00:00
RUN go build .
DRY out the Dockefile.build
2024-01-07 00:46:55 +00:00
FROM --platform=linux/arm64 cpu-build-arm64 AS build-arm64
update build
2024-01-04 21:25:38 +00:00
ENV CGO_ENABLED 1
ARG GOLANG_VERSION
ARG GOFLAGS
Add multiple CPU variants for Intel Mac This also refines the build process for the ext_server build.
2024-01-13 00:28:00 +00:00
ARG CGO_CFLAGS
update build
2024-01-04 21:25:38 +00:00
WORKDIR /go/src/github.com/jmorganca/ollama
COPY . .
Support multiple variants for a given llm lib type In some cases we may want multiple variants for a given GPU type or CPU. This adds logic to have an optional Variant which we can use to select an optimal library, but also allows us to try multiple variants in case some fail to load. This can be useful for scenarios such as ROCm v5 vs v6 incompatibility or potentially CPU features.
2024-01-05 20:13:08 +00:00
COPY --from=cuda-build-arm64 /go/src/github.com/jmorganca/ollama/llm/llama.cpp/build/linux/ llm/llama.cpp/build/linux/
update build
2024-01-04 21:25:38 +00:00
RUN go build .
update build_darwin.sh
2023-09-26 17:38:32 +00:00
update build
2024-01-04 21:25:38 +00:00
FROM build-$TARGETARCH
Reference in a new issue Copy permalink