docker : add GGML_CPU_ARM_ARCH arg to select ARM architecture#11419
docker : add GGML_CPU_ARM_ARCH arg to select ARM architecture#11419
Conversation
|
I'm testing it on my cloned repo |
|
It worked, so I'm merging it now. Thanks. |
|
Not entirely sure why, but CI to build docker still fails with At this point, the only explanation I can think of is that something happening at runner's hardware level |
|
That's weird, I also tested it locally and it completes successfully on my machine with QEMU. |
|
Hmm sorry I overlooked a bit, the scheduled build failed on my clone repo too: https://github.com/ngxson/llama.cpp/actions/workflows/docker.yml I'm re-running another build from xsn/test_docker_arm branch which is known to work yesterday. If it doesn't work, there is definitely something to do with runner's hardware: https://github.com/ngxson/llama.cpp/actions/runs/12976884398 |
|
If that doesn't work, may be worth to try disabling the cache, or building each platform separately in sequence. |
|
It fails, I'm running another one with AMD/ARM as separated jobs: https://github.com/ngxson/llama.cpp/actions/runs/12977065608 |
cont #11403