llama.cpp

6f1d9d71 - Fix Docker ROCM builds, use AMDGPU_TARGETS instead of GPU_TARGETS (#9641)

Fix Docker ROCM builds, use AMDGPU_TARGETS instead of GPU_TARGETS (#9641) * Fix Docker ROCM builds, use AMDGPU_TARGETS instead of GPU_TARGETS * Set ROCM_DOCKER_ARCH as string due it incorrectly build and cause OOM exit code