-
Notifications
You must be signed in to change notification settings - Fork 9.7k
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Illegal hardware instruction in quantize step #41
Comments
What does |
This error happens when binary is compiled for x86_64 instead of arm64. This is common mistake if you are compiling under conda like environment. Check binary quantize with: On Apple Silicon Macs it should print: If it shows x86_64 then you have to recompile after exiting conda environment: |
@prusnak it said
|
Solved by re-install |
Thank you, it works as you said. |
@brozkrut I got the error in Windows 7:
when I executed :
and I checked my quantize file:
But the architecture of docker image named ghcr.io/ggerganov/llama.cpp:full is amd64:
and my environment is:
SO I'M CONFUSED: |
|
can you please explain me |
What I've tried:
main
on themodel-f16
, still have the same error13B
model, still same error inquantize
stepEnv:
Darwin Tungs-MacBook-Pro.local 21.6.0 Darwin Kernel Version 21.6.0: Sat Jun 18 17:07:22 PDT 2022; root:xnu-8020.140.41~1/RELEASE_ARM64_T6000 x86_64
The text was updated successfully, but these errors were encountered: