I did a fresh installation of Nexa (v0.0.9.2) on MacOs Montery with Apple M1 Pro chip with the command from the documentation:
CMAKE_ARGS="-DGGML_METAL=ON -DSD_METAL=ON" pip install nexaai --prefer-binary --index-url https://nexaai.github.io/nexa-sdk/whl/metal --extra-index-url https://pypi.org/simple --no-cache-dir
Everything went smoothly without error with the following logs:
I did a fresh installation of Nexa (v0.0.9.2) on MacOs Montery with Apple M1 Pro chip with the command from the documentation:
CMAKE_ARGS="-DGGML_METAL=ON -DSD_METAL=ON" pip install nexaai --prefer-binary --index-url https://nexaai.github.io/nexa-sdk/whl/metal --extra-index-url https://pypi.org/simple --no-cache-dir
Everything went smoothly without error with the following logs:
Trying to load a model like
nexa run llama2
gives me the following error:Why
but is an incompatible architecture (have (x86_64), need (arm64e)))
as I installed the version for M1 arm ?The similar error is for other model
nexa run sd1-4
: