github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-05 23:53:43 -05:00
Code Issues 14.5k Packages Projects Releases 120 Wiki Activity

[GH-ISSUE #6892] Build CPU only image #4361

New Issue
Open
opened 2026-04-12 15:18:02 -05:00 by GiteaMirror · 1 comment
GiteaMirror commented 2026-04-12 15:18:02 -05:00
Owner
Copy Link

Originally created by @mgiessing on GitHub (Sep 20, 2024).
Original GitHub issue: https://github.com/ollama/ollama/issues/6892

Originally assigned to: @dhiltgen on GitHub.

What is the issue?

I'd be interested in only building a CPU docker image for ppc arch. I tried to do that for arm64 but it doesn't work perfectly either so I'm wondering if that is possible at all with only one big Dockerfile as it is now?

Ideally I'd like to have something like PLATFORM=linux/arm64 TARGETARCH=arm64 DEVICE=cpu scripts/build_docker.sh

Maybe someone can enlighten me how to do this.

Thank you!

OS

Linux, Docker

GPU

No response

CPU

Other

Ollama version

0.3.11

Originally created by @mgiessing on GitHub (Sep 20, 2024). Original GitHub issue: https://github.com/ollama/ollama/issues/6892 Originally assigned to: @dhiltgen on GitHub. ### What is the issue? I'd be interested in only building a CPU docker image for ppc arch. I tried to do that for arm64 but it doesn't work perfectly either so I'm wondering if that is possible at all with only one big Dockerfile as it is now? Ideally I'd like to have something like `PLATFORM=linux/arm64 TARGETARCH=arm64 DEVICE=cpu scripts/build_docker.sh` Maybe someone can enlighten me how to do this. Thank you! ### OS Linux, Docker ### GPU _No response_ ### CPU Other ### Ollama version 0.3.11
GiteaMirror added the dockerlinuxfeature request labels 2026-04-12 15:18:02 -05:00
GiteaMirror commented 2026-04-12 15:18:04 -05:00
Author
Owner
Copy Link

@dhiltgen commented on GitHub (Sep 20, 2024):

We're working on some changes to the build setup that may make this a bit easier to accomplish. Until then, you can take a look at the Dockerfile and in the runtime-arm64 target, comment out the two cuda COPY commands and that should get you an arm64 container image with just the CPU runner.

<!-- gh-comment-id:2364744743 --> @dhiltgen commented on GitHub (Sep 20, 2024): We're working on some changes to the build setup that may make this a bit easier to accomplish. Until then, you can take a look at the Dockerfile and in the `runtime-arm64` target, comment out the two cuda `COPY` commands and that should get you an arm64 container image with just the CPU runner.
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 docker feature request linux
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#4361
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?