Gentoo Packages

sci-ml/llama-cpp: Build a HIP (ROCm) backend
sci-ml/ollama-bin: Enable AMD ROCm GPU acceleration support. Requires compatible AMD GPU (Radeon RX 6000 series or newer, or Radeon VII) and ROCm libraries. May require HSA_OVERRIDE_GFX_VERSION environment variable for optimal compatibility. This is experimental and not all GPU models are supported.

sci-ml/llama-cpp: Build a HIP (ROCm) backend
sci-ml/ollama-bin: Enable AMD ROCm GPU acceleration support. Requires compatible AMD GPU (Radeon RX 6000 series or newer, or Radeon VII) and ROCm libraries. May require HSA_OVERRIDE_GFX_VERSION environment variable for optimal compatibility. This is experimental and not all GPU models are supported.

Package	Local Description (use.local.desc)	Metadata Description (metadata.xml)
sci-ml/llama-cpp	Build a HIP (ROCm) backend	Build a HIP (ROCm) backend
sci-ml/ollama-bin	Enable AMD ROCm GPU acceleration support. Requires compatible AMD GPU (Radeon RX 6000 series or newer, or Radeon VII) and ROCm libraries. May require HSA_OVERRIDE_GFX_VERSION environment variable for optimal compatibility. This is experimental and not all GPU models are supported.	Enable AMD ROCm GPU acceleration support. Requires compatible AMD GPU (Radeon RX 6000 series or newer, or Radeon VII) and ROCm libraries. May require HSA_OVERRIDE_GFX_VERSION environment variable for optimal compatibility. This is experimental and not all GPU models are supported.

USE Flag: rocm