abetlen / abetlen/llama-cpp-python
CMAKE config for Ninja unsuitable for compiling on Ryzen 5 6 core cpu
- Dominant language
- Python
- Stars
- 10.6k
- Forks
- 1.4k
- PR merge metrics
- PR metrics pending
Description
Hi thanks for all you great work at providing a wrapper with a web server. I got the wrapper working on my cpu but I have a ROCm system. I have llama.cpp fully working on my GPU so I have tried to compile llama_cpp_python with
`
CMAKE_ARGS="-DLLAMA_HIPBLAS=on" pip install llama-cpp-python[server] --force-reinstall --upgrade --no-cache-dir `
However this gets stuck as my cpu has 6 cores and I think Ninja is using 100% of these threads and this results in the following:
` vendor/llama.cpp/CMakeFiles/llama.dir/llama.cpp.o -c /tmp/pip-install-nijs8rwv/llama-cpp-python_6a0e9af7a84f46bd933b9ed621d1d190/vendor/llama.cpp/llama.cpp
ninja: build stopped: subcommand failed.
*** CMake build failed
[end of output]
note: This error originates from a subprocess, and is likely not a problem with pip.
ERROR: Failed building wheel for llama-cpp-python
Failed to build llama-cpp-python
ERROR: Could not build wheels for llama-cpp-python, which is required to install pyproject.toml-based projects `
Hope you can advise. I need to know how to specify to cmake to use fewer threads I think. Alas the options
`--build -j nthreads`
Doesnt work. I am using a 6 core amd Ryzen 5 setup
Contributor guide
Assessment
This issue has not been assessed yet.