llama.cpp
llama.cpp copied to clipboard
M1 Max + GNU coreutils: "Your arch is announced as x86_64, but it seems to actually be ARM64"
When I build, the makefile detects my M1 Max as 86_64.
This is because I have GNU coreutils uname
on my PATH
, which announces my architecture as arm64
(whereas the system distribution of uname
would call the same architecture arm
).
https://github.com/Lightning-AI/lightning/pull/13992#issuecomment-1204157830
https://github.com/Lightning-AI/lightning/issues/13991
this condition needs widening to accept both arm
and arm64
:
https://github.com/ggerganov/llama.cpp/blob/c09a9cfb06c87d114615c105adda91b0e6273b69/Makefile