github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-08 00:51:34 -05:00
Code Issues 14.5k Packages Projects Releases 120 Wiki Activity

[GH-ISSUE #5039] How to only run the amd64 cpu version of ollama's docker image? #28945

New Issue
Closed
opened 2026-04-22 07:30:50 -05:00 by GiteaMirror · 3 comments
GiteaMirror commented 2026-04-22 07:30:50 -05:00
Owner
Copy Link

Originally created by @musarehmani291 on GitHub (Jun 14, 2024).
Original GitHub issue: https://github.com/ollama/ollama/issues/5039

Originally assigned to: @dhiltgen on GitHub.

What is the issue?

Hi guys, I deployed ollama using the exact dockerfile available on your repo without any changes. my server architecture is amd64 cpu. when I tried to build it, it keeps building. what should I do? any help would be appreciated.

OS

Docker

GPU

No response

CPU

AMD

Ollama version

No response

Originally created by @musarehmani291 on GitHub (Jun 14, 2024). Original GitHub issue: https://github.com/ollama/ollama/issues/5039 Originally assigned to: @dhiltgen on GitHub. ### What is the issue? Hi guys, I deployed ollama using the exact dockerfile available on your repo without any changes. my server architecture is amd64 cpu. when I tried to build it, it keeps building. what should I do? any help would be appreciated. ### OS Docker ### GPU _No response_ ### CPU AMD ### Ollama version _No response_
GiteaMirror added the question label 2026-04-22 07:30:50 -05:00
GiteaMirror commented 2026-04-22 07:30:51 -05:00
Author
Owner
Copy Link

@dhiltgen commented on GitHub (Jun 14, 2024):

Our Dockerfile is designed to build both arm and x86 images. We use the build_docker.sh script on ARM Mac's to generate multi-arch images to upload to Docker Hub. You can use that script directly, or use it for inspiration on the manual docker build ... arguments to generate an image from the source.

<!-- gh-comment-id:2168362399 --> @dhiltgen commented on GitHub (Jun 14, 2024): Our Dockerfile is designed to build both arm and x86 images. We use the [build_docker.sh](https://github.com/ollama/ollama/blob/main/scripts/build_docker.sh) script on ARM Mac's to generate multi-arch images to upload to Docker Hub. You can use that script directly, or use it for inspiration on the manual `docker build ...` arguments to generate an image from the source.
GiteaMirror commented 2026-04-22 07:30:52 -05:00
Author
Owner
Copy Link

@musarehmani291 commented on GitHub (Jun 14, 2024):

Hi @dhiltgen
I wanna deploy ollama to hugging face spaces using docker sdk so I'm using the default dockerfile of this repo but, the problem with this dockerfile is that it builds image for every architecture but, I don't want that. My huggingface architecture is amd64. so, is there a way to get the docker file to build the image only for that architecture? Mind you, I've not made any changes to the dockerfile. can you tell me how do I set the target architecture?

ARG GOLANG_VERSION=1.22.1
ARG CMAKE_VERSION=3.22.1

this CUDA_VERSION corresponds with the one specified in docs/gpu.md

ARG CUDA_VERSION=11.3.1
ARG ROCM_VERSION=6.0.2

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/ollama/ollama/
WORKDIR /go/src/github.com/ollama/ollama/llm/generate
ARG CGO_CFLAGS
RUN OLLAMA_SKIP_STATIC_GENERATE=1 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/ollama/ollama/
WORKDIR /go/src/github.com/ollama/ollama/llm/generate
ARG CGO_CFLAGS
RUN OLLAMA_SKIP_STATIC_GENERATE=1 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/ollama/ollama/
WORKDIR /go/src/github.com/ollama/ollama/llm/generate
ARG CGO_CFLAGS
ARG AMDGPU_TARGETS
RUN OLLAMA_SKIP_STATIC_GENERATE=1 OLLAMA_SKIP_CPU_GENERATE=1 sh gen_linux.sh
RUN mkdir /tmp/scratch &&
for dep in $(zcat /go/src/github.com/ollama/ollama/llm/build/linux/x86_64/rocm*/bin/deps.txt.gz) ; 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/ollama/ollama/dist/deps/ &&
(cd /tmp/scratch/ && tar czvf /go/src/github.com/ollama/ollama/dist/deps/ollama-linux-amd64-rocm.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/ollama/ollama/
ARG OLLAMA_CUSTOM_CPU_DEFS
ARG CGO_CFLAGS
WORKDIR /go/src/github.com/ollama/ollama/llm/generate

FROM --platform=linux/amd64 cpu-builder-amd64 AS static-build-amd64
RUN OLLAMA_CPU_TARGET="static" sh gen_linux.sh
FROM --platform=linux/amd64 cpu-builder-amd64 AS cpu-build-amd64
RUN OLLAMA_SKIP_STATIC_GENERATE=1 OLLAMA_CPU_TARGET="cpu" sh gen_linux.sh
FROM --platform=linux/amd64 cpu-builder-amd64 AS cpu_avx-build-amd64
RUN OLLAMA_SKIP_STATIC_GENERATE=1 OLLAMA_CPU_TARGET="cpu_avx" sh gen_linux.sh
FROM --platform=linux/amd64 cpu-builder-amd64 AS cpu_avx2-build-amd64
RUN OLLAMA_SKIP_STATIC_GENERATE=1 OLLAMA_CPU_TARGET="cpu_avx2" sh gen_linux.sh

FROM --platform=linux/arm64 centos:7 AS cpu-builder-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/ollama/ollama/
ARG OLLAMA_CUSTOM_CPU_DEFS
ARG CGO_CFLAGS
WORKDIR /go/src/github.com/ollama/ollama/llm/generate

FROM --platform=linux/arm64 cpu-builder-arm64 AS static-build-arm64
RUN OLLAMA_CPU_TARGET="static" sh gen_linux.sh
FROM --platform=linux/arm64 cpu-builder-arm64 AS cpu-build-arm64
RUN OLLAMA_SKIP_STATIC_GENERATE=1 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/ollama/ollama
COPY . .
COPY --from=static-build-amd64 /go/src/github.com/ollama/ollama/llm/build/linux/ llm/build/linux/
COPY --from=cpu_avx-build-amd64 /go/src/github.com/ollama/ollama/llm/build/linux/ llm/build/linux/
COPY --from=cpu_avx2-build-amd64 /go/src/github.com/ollama/ollama/llm/build/linux/ llm/build/linux/
COPY --from=cuda-build-amd64 /go/src/github.com/ollama/ollama/llm/build/linux/ llm/build/linux/
COPY --from=rocm-build-amd64 /go/src/github.com/ollama/ollama/llm/build/linux/ llm/build/linux/
COPY --from=rocm-build-amd64 /go/src/github.com/ollama/ollama/dist/deps/ ./dist/deps/
ARG GOFLAGS
ARG CGO_CFLAGS
RUN go build -trimpath .

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/ollama/ollama
COPY . .
COPY --from=static-build-arm64 /go/src/github.com/ollama/ollama/llm/build/linux/ llm/build/linux/
COPY --from=cuda-build-arm64 /go/src/github.com/ollama/ollama/llm/build/linux/ llm/build/linux/
ARG GOFLAGS
ARG CGO_CFLAGS
RUN go build -trimpath .

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/ollama/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/ollama/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/ollama/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"]

<!-- gh-comment-id:2168527938 --> @musarehmani291 commented on GitHub (Jun 14, 2024): Hi @dhiltgen I wanna deploy ollama to hugging face spaces using docker sdk so I'm using the default dockerfile of this repo but, the problem with this dockerfile is that it builds image for every architecture but, I don't want that. My huggingface architecture is amd64. so, is there a way to get the docker file to build the image only for that architecture? Mind you, I've not made any changes to the dockerfile. can you tell me how do I set the target architecture? ARG GOLANG_VERSION=1.22.1 ARG CMAKE_VERSION=3.22.1 # this CUDA_VERSION corresponds with the one specified in docs/gpu.md ARG CUDA_VERSION=11.3.1 ARG ROCM_VERSION=6.0.2 # 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:$PATH COPY --from=llm-code / /go/src/github.com/ollama/ollama/ WORKDIR /go/src/github.com/ollama/ollama/llm/generate ARG CGO_CFLAGS RUN OLLAMA_SKIP_STATIC_GENERATE=1 OLLAMA_SKIP_CPU_GENERATE=1 sh gen_linux.sh FROM --platform=linux/arm64 nvidia/cuda:$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/ollama/ollama/ WORKDIR /go/src/github.com/ollama/ollama/llm/generate ARG CGO_CFLAGS RUN OLLAMA_SKIP_STATIC_GENERATE=1 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/ollama/ollama/ WORKDIR /go/src/github.com/ollama/ollama/llm/generate ARG CGO_CFLAGS ARG AMDGPU_TARGETS RUN OLLAMA_SKIP_STATIC_GENERATE=1 OLLAMA_SKIP_CPU_GENERATE=1 sh gen_linux.sh RUN mkdir /tmp/scratch && \ for dep in $(zcat /go/src/github.com/ollama/ollama/llm/build/linux/x86_64/rocm*/bin/deps.txt.gz) ; do \ cp ${dep} /tmp/scratch/ || exit 1 ; \ done && \ (cd /opt/rocm/lib && tar cf - rocblas/library) | (cd /tmp/scratch/ && tar xf - ) && \ mkdir -p /go/src/github.com/ollama/ollama/dist/deps/ && \ (cd /tmp/scratch/ && tar czvf /go/src/github.com/ollama/ollama/dist/deps/ollama-linux-amd64-rocm.tgz . ) FROM --platform=linux/amd64 centos:7 AS cpu-builder-amd64 ARG CMAKE_VERSION ARG GOLANG_VERSION COPY ./scripts/rh_linux_deps.sh / RUN CMAKE_VERSION=${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/ollama/ollama/ ARG OLLAMA_CUSTOM_CPU_DEFS ARG CGO_CFLAGS WORKDIR /go/src/github.com/ollama/ollama/llm/generate FROM --platform=linux/amd64 cpu-builder-amd64 AS static-build-amd64 RUN OLLAMA_CPU_TARGET="static" sh gen_linux.sh FROM --platform=linux/amd64 cpu-builder-amd64 AS cpu-build-amd64 RUN OLLAMA_SKIP_STATIC_GENERATE=1 OLLAMA_CPU_TARGET="cpu" sh gen_linux.sh FROM --platform=linux/amd64 cpu-builder-amd64 AS cpu_avx-build-amd64 RUN OLLAMA_SKIP_STATIC_GENERATE=1 OLLAMA_CPU_TARGET="cpu_avx" sh gen_linux.sh FROM --platform=linux/amd64 cpu-builder-amd64 AS cpu_avx2-build-amd64 RUN OLLAMA_SKIP_STATIC_GENERATE=1 OLLAMA_CPU_TARGET="cpu_avx2" sh gen_linux.sh FROM --platform=linux/arm64 centos:7 AS cpu-builder-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/ollama/ollama/ ARG OLLAMA_CUSTOM_CPU_DEFS ARG CGO_CFLAGS WORKDIR /go/src/github.com/ollama/ollama/llm/generate FROM --platform=linux/arm64 cpu-builder-arm64 AS static-build-arm64 RUN OLLAMA_CPU_TARGET="static" sh gen_linux.sh FROM --platform=linux/arm64 cpu-builder-arm64 AS cpu-build-arm64 RUN OLLAMA_SKIP_STATIC_GENERATE=1 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/ollama/ollama COPY . . COPY --from=static-build-amd64 /go/src/github.com/ollama/ollama/llm/build/linux/ llm/build/linux/ COPY --from=cpu_avx-build-amd64 /go/src/github.com/ollama/ollama/llm/build/linux/ llm/build/linux/ COPY --from=cpu_avx2-build-amd64 /go/src/github.com/ollama/ollama/llm/build/linux/ llm/build/linux/ COPY --from=cuda-build-amd64 /go/src/github.com/ollama/ollama/llm/build/linux/ llm/build/linux/ COPY --from=rocm-build-amd64 /go/src/github.com/ollama/ollama/llm/build/linux/ llm/build/linux/ COPY --from=rocm-build-amd64 /go/src/github.com/ollama/ollama/dist/deps/ ./dist/deps/ ARG GOFLAGS ARG CGO_CFLAGS RUN go build -trimpath . # 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/ollama/ollama COPY . . COPY --from=static-build-arm64 /go/src/github.com/ollama/ollama/llm/build/linux/ llm/build/linux/ COPY --from=cuda-build-arm64 /go/src/github.com/ollama/ollama/llm/build/linux/ llm/build/linux/ ARG GOFLAGS ARG CGO_CFLAGS RUN go build -trimpath . # 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/ollama/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/ollama/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/ollama/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"]
GiteaMirror commented 2026-04-22 07:30:52 -05:00
Author
Owner
Copy Link

@dhiltgen commented on GitHub (Jun 19, 2024):

can you tell me how do I set the target architecture?

If you're using our build script, you can use BUILD_ARCH=amd64 ./scripts/build_linux.sh

I'm not sure what your trying to accomplish, but if you don't need to build from source, you can just

FROM ollama/ollama:latest

in your Dockerfile and pick up our pre-built binaries from Docker Hub

<!-- gh-comment-id:2177314506 --> @dhiltgen commented on GitHub (Jun 19, 2024): > can you tell me how do I set the target architecture? If you're using our build script, you can use `BUILD_ARCH=amd64 ./scripts/build_linux.sh` I'm not sure what your trying to accomplish, but if you don't need to build from source, you can just ``` FROM ollama/ollama:latest ``` in your Dockerfile and pick up our pre-built binaries from [Docker Hub](https://hub.docker.com/r/ollama/ollama)
Sign in to join this conversation.
No Branch/Tag Specified
Branches Tags
Labels
Clear labels
amd
api
app
bug
build
cli
cloud
compatibility
context-length
create
docker
documentation
embeddings
feature request
feedback wanted
good first issue
gpt-oss
gpu
harmony
help wanted
image
install
intel
js
launch
linux
macos
memory
mlx
model
needs more info
networking
nvidia
ollama.com
performance
pull-request
Mirrored from GitHub Pull Request
 python
question
registry
rendering
thinking
tools
top
vulkan
windows
wsl
No Label question
Milestone
No items
No Milestone
Projects
Clear projects
No project
Assignees
Clear assignees
GiteaMirror ninjasurge
No Assignees
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: github-starred/ollama#28945
Delete Branch "%!s()"

Deleting a branch is permanent. Although the deleted branch may continue to exist for a short time before it actually gets removed, it CANNOT be undone in most cases. Continue?