-
Notifications
You must be signed in to change notification settings - Fork 959
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
Build failiure on armv7 (docker) #17
Comments
Try with the following commands: git clone https://github.com/ggerganov/ggml
cd ggml
# build gpt-2
gcc -std=c11 -O3 -I include/ggml/ -pthread -mfpu=neon-fp-armv8 -mfp16-format=ieee -mno-unaligned-access -funsafe-math-optimizations -c src/ggml.c -o ggml.o
g++ -O3 -pthread -I include/ -I examples/ examples/gpt-2/main.cpp examples/utils.cpp ggml.o -o gpt-2
# download model
./examples/gpt-2/download-ggml-model.sh 117M
# run with default parameters
./gpt-2 |
Sadly, it still failed. Also, would the resulting binary work on armv7? Are those older phones using it, like the Nexus 5, even powerful enough for these models? Logs
|
These were the commands that I used to make it run on Raspberry Pi 4 and it worked. I was hoping it would work in your case too, but likely some flag is missing. You can build this code for pretty much every device you want. |
Hi! Thank you for your work on ggml and whisper.cpp, these two amazing projects really did wonders for the performance. I tried compiling the examples to see if they can be run on an Ubuntu Touch phone, which is essentially an Ubuntu 16.04 LTS Core on arm. Sadly, the build failed due to not finding
immintrin.h
, which as far as I understood is present only on x84 systems. As you can tell, I am a novice, so I'd appreciate any help regarding this. Once again, thanks for all your work! :)Logs
The text was updated successfully, but these errors were encountered: