llama-cpp-python icon indicating copy to clipboard operation
llama-cpp-python copied to clipboard

Published 20 hours ago • verified publisher icon abetlen

Change the command to `CMAKE_ARGS="-DGGML_CUDA=on -DLLAVA_BUILD=off" pip install -U llama-cpp-python --force-reinstall --no-cache-dir` solved the problem.

Open yimuu opened this issue 5 months ago • 1 comments 

          Change the command to `CMAKE_ARGS="-DGGML_CUDA=on -DLLAVA_BUILD=off" pip install -U llama-cpp-python --force-reinstall --no-cache-dir` solved the problem.

Originally posted by @blx0102 in https://github.com/abetlen/llama-cpp-python/issues/1639#issuecomment-2257757873

can not find libllava.so

yimuu avatar Sep 22 '24 08:09 yimuu