github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-07 00:22:43 -05:00
Code Issues 14.5k Packages Projects Releases 120 Wiki Activity

[GH-ISSUE #2579] Use pkg-config to find llama-cpp libs #48029

New Issue
Closed
opened 2026-04-28 06:28:40 -05:00 by GiteaMirror · 1 comment
GiteaMirror commented 2026-04-28 06:28:40 -05:00
Owner
Copy Link

Originally created by @happysalada on GitHub (Feb 18, 2024).
Original GitHub issue: https://github.com/ollama/ollama/issues/2579

Hi first of all, thank you for ollama, its amazing !

Im one of the person trying to maintain this on nixos. Since 0.1.19 i think llama-cpp is directly included as a submodule in the repo. Also the .so objects are directly referenced by path in the go build files. Would it be possible to use pkg-config to find those files ?
This would make building ollama from source much easier as llama-cpp can just be specified as a dependency.

I understand that you might have a million more important things to do, i just want to start the discussion.

Originally created by @happysalada on GitHub (Feb 18, 2024). Original GitHub issue: https://github.com/ollama/ollama/issues/2579 Hi first of all, thank you for ollama, its amazing ! Im one of the person trying to maintain this on nixos. Since 0.1.19 i think llama-cpp is directly included as a submodule in the repo. Also the .so objects are directly referenced by path in the go build files. Would it be possible to use pkg-config to find those files ? This would make building ollama from source much easier as llama-cpp can just be specified as a dependency. I understand that you might have a million more important things to do, i just want to start the discussion.
GiteaMirror added the feature request label 2026-04-28 06:28:40 -05:00
GiteaMirror commented 2026-04-28 06:28:44 -05:00
Author
Owner
Copy Link

@dhiltgen commented on GitHub (Oct 23, 2024):

We've switched to a vendored model for llama.cpp as we need to apply patches for it to work with Ollama. Using an unmodified upstream version of llama.cpp wont be possible. You should give the new build process a try.

https://github.com/ollama/ollama/blob/main/docs/development.md#transition-to-go-runner

<!-- gh-comment-id:2433010076 --> @dhiltgen commented on GitHub (Oct 23, 2024): We've switched to a vendored model for llama.cpp as we need to apply patches for it to work with Ollama. Using an unmodified upstream version of llama.cpp wont be possible. You should give the new build process a try. https://github.com/ollama/ollama/blob/main/docs/development.md#transition-to-go-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 feature request
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#48029
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?