Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Bug: llama.cpp binaries are compiled dynamically and the library is missing! #8161

Closed
0wwafa opened this issue Jun 27, 2024 · 9 comments
Closed
Labels
bug-unconfirmed critical severity Used to report critical severity bugs in llama.cpp (e.g. Crashing, Corrupted, Dataloss)

Comments

@0wwafa
Copy link

0wwafa commented Jun 27, 2024

What happened?

$ ./build/bin/llama-quantize -h
./build/bin/llama-quantize: error while loading shared libraries: libllama.so: cannot open shared object file: No such file or directory

Name and Version

latest

What operating system are you seeing the problem on?

No response

Relevant log output

see up.
@0wwafa 0wwafa added bug-unconfirmed critical severity Used to report critical severity bugs in llama.cpp (e.g. Crashing, Corrupted, Dataloss) labels Jun 27, 2024
@loonerin
Copy link
Contributor

Confirmed. #8006 breaks the github release builds.

@0wwafa
Copy link
Author

0wwafa commented Jun 28, 2024

Confirmed. #8006 breaks the github release builds.

bug still present.

@slaren
Copy link
Collaborator

slaren commented Jun 28, 2024

Fixed in #8170

@slaren slaren closed this as completed Jun 28, 2024
@hackey
Copy link

hackey commented Jun 28, 2024

Fixed in #8170

I still get an error after building. I checked 10 minutes ago.

@SignalRT
Copy link

SignalRT commented Jul 1, 2024

@slaren It seems that the problem remains in MacOS (at least). I'm not able to build the dynamic link libraries.

@slaren
Copy link
Collaborator

slaren commented Jul 1, 2024

The macOS releases are no longer built with dynamic libraries. If you are experiencing a different problem, please open a new issue and explain it in detail.

@splitpierre
Copy link

I'm having the libllama.so missing while trying to build and run the llama-server-vulkan.Dockerfile image on Linux.
Currently using vulkan in earlier tag b2288. 😞

@pritam-dey3
Copy link

I'm having the libllama.so missing while trying to build and run the llama-server-vulkan.Dockerfile image on Linux. Currently using vulkan in earlier tag b2288. 😞

I can confirm this. I am getting the same error.
/llama-server: error while loading shared libraries: libllama.so: cannot open shared object file: No such file or directory

@bensuperpc
Copy link

bensuperpc commented Aug 3, 2024

I also have the same problem on linux system with 76614f3 :/

Commands used:

cmake -B build -S . -G Ninja
cmake --build build --config Release
./build/bin/llama-cli

Result:

bensuperpc@raspberrypi:~/dockcross/llama.cpp $ ./build/bin/llama-cli -v
./build/bin/llama-cli: error while loading shared libraries: libllama.so: cannot open shared object file: No such file or directory

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
bug-unconfirmed critical severity Used to report critical severity bugs in llama.cpp (e.g. Crashing, Corrupted, Dataloss)
Projects
None yet
Development

No branches or pull requests

8 participants