github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-06 16:11:34 -05:00
Code Issues 14.5k Packages Projects Releases 120 Wiki Activity

[GH-ISSUE #2628] libext_server.a(llava.cpp.o) { in archive is not an object | not an ELF file } #48064

New Issue
Closed
opened 2026-04-28 06:36:39 -05:00 by GiteaMirror · 2 comments
GiteaMirror commented 2026-04-28 06:36:39 -05:00
Owner
Copy Link

Originally created by @pavelsr on GitHub (Feb 21, 2024).
Original GitHub issue: https://github.com/ollama/ollama/issues/2628

Originally assigned to: @dhiltgen on GitHub.

I'm trying to build ollama with AMD GPU support via command

ROCM_PATH=/opt/rocm CLBlast_DIR=/usr/lib/x86_64-linux-gnu/cmake/CLBlast go generate -tags rocm ./...

and in final stage of build I got an error mentioned in issue header:

Screenshot from 2024-02-21 12-55-49

I tried to replace g++ with clang++ at llm/generate/gen_common.sh as it was mentioned in this comment but error in the end of build is still same.

Adding -fcf-protection=none also wasn't helped, just changed error message a little bit

ld.lld: error: ../llama.cpp/build/linux/x86_64/cpu/examples/server/libext_server.a(llava.cpp.o): not an ELF file
clang++: error: linker command failed with exit code 1 (use -v to see invocation)

What do I need to fix for proper compiling of ext_server static library ?

Seems like issue related to this part of ollama sources

Originally created by @pavelsr on GitHub (Feb 21, 2024). Original GitHub issue: https://github.com/ollama/ollama/issues/2628 Originally assigned to: @dhiltgen on GitHub. I'm trying to build ollama with AMD GPU support via command ``` ROCM_PATH=/opt/rocm CLBlast_DIR=/usr/lib/x86_64-linux-gnu/cmake/CLBlast go generate -tags rocm ./... ``` and in final stage of build I got an error mentioned in issue header: ![Screenshot from 2024-02-21 12-55-49](https://github.com/ollama/ollama/assets/1158473/93468605-6b88-4029-a890-793d135e6e48) I tried to replace `g++` with `clang++` at llm/generate/gen_common.sh as it was mentioned in [this comment](https://github.com/ollama/ollama/issues/2473#issuecomment-1942090475) but error in the end of build is still same. [Adding](https://github.com/ollama/ollama/issues/2473#issuecomment-1941640723) `-fcf-protection=none` also wasn't helped, just changed error message a little bit ``` ld.lld: error: ../llama.cpp/build/linux/x86_64/cpu/examples/server/libext_server.a(llava.cpp.o): not an ELF file clang++: error: linker command failed with exit code 1 (use -v to see invocation) ``` What do I need to fix for proper compiling of ext_server static library ? Seems like issue related to [this part of ollama sources](https://github.com/ollama/ollama/blob/e1f50377f499b1784a866a6463af364987443238/llm/generate/gen_common.sh#L89)
GiteaMirror added the question label 2026-04-28 06:36:39 -05:00
GiteaMirror commented 2026-04-28 06:36:42 -05:00
Author
Owner
Copy Link

@dhiltgen commented on GitHub (Feb 26, 2024):

If you run the go generate ./... with CGO_CFLAGS="-g" that will increase verbosity of the build logs which might help shed some light on what's going wrong.

<!-- gh-comment-id:1964928353 --> @dhiltgen commented on GitHub (Feb 26, 2024): If you run the `go generate ./...` with `CGO_CFLAGS="-g"` that will increase verbosity of the build logs which might help shed some light on what's going wrong.
GiteaMirror commented 2026-04-28 06:36:43 -05:00
Author
Owner
Copy Link

@dhiltgen commented on GitHub (Mar 27, 2024):

If you're still having trouble building from source, please let us know.

<!-- gh-comment-id:2023969236 --> @dhiltgen commented on GitHub (Mar 27, 2024): If you're still having trouble building from source, please let us know.
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#48064
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?