CPU-only
While this repo is focused on providing cuBLAS wheels, it has become evident that there is a need for CPU-only wheels that do not require AVX2.
Wheels can be more easily downloaded from: https://jllllll.github.io/llama-cpp-python-cuBLAS-wheels/AVX/cpu
Replace AVX
with one of basic
, AVX2
or AVX512
depending on what your CPU supports.