Gentoo Packages

sci-ml/llama-cpp: ggml: use HIP unified memory architecture : from docs/build.md : On Linux it is also possible to use unified memory architecture (UMA) to share main memory between the CPU and integrated GPU by setting -DGGML_HIP_UMA=ON. However, this hurts performance for non-integrated GPUs (but enables working with integrated GPUs).

Warning: USE flag 'hip-uma' is used in ebuilds/metadata but is not defined in profiles/use.desc

Package	Local Description (use.local.desc)	Metadata Description (metadata.xml)
sci-ml/llama-cpp	-	ggml: use HIP unified memory architecture : from docs/build.md : On Linux it is also possible to use unified memory architecture (UMA) to share main memory between the CPU and integrated GPU by setting -DGGML_HIP_UMA=ON. However, this hurts performance for non-integrated GPUs (but enables working with integrated GPUs).

USE Flag: hip-uma