mirror of
https://github.com/ggml-org/llama.cpp.git
synced 2026-09-13 02:10:45 +02:00
6f1d9d71f4
* 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