mirror of
https://github.com/ggerganov/whisper.cpp.git
synced 2025-05-02 16:53:08 +00:00
Replace compile-time `GGML_HIP_UMA` with environment variable `GGML_CUDA_ENABLE_UNIFIED_MEMORY`. This unifies the usage on NVIDIA and AMD GPUs, and allows a single binary to be shared between integrated and dedicated GPUs.