abetlen / abetlen/llama-cpp-python

CMAKE config for Ninja unsuitable for compiling on Ryzen 5 6 core cpu

Abierto
#895 1 comentario 0 reacciones 0 asignados Ver en GitHub
bug build
Lenguaje dominante
Python
Estrellas
10.6k
Forks
1.4k
Métricas de merge de PR
Métricas de PR pendientes

Descripción

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

Guía de contribución

Abrir la guía de contribución

Evaluación

Este issue todavía no se ha evaluado.

Recibe los nuevos issues en tu correo

Un resumen breve de issues de GitHub para principiantes.