FICHA · AUR

python-llama-cpp-hip

Python bindings for llama.cpp (with HIP/ROCM support)

  • ROCm llama.cpp bindings
  • LIBRARY
  • AI
  • HARDWARE
  • Dependency only
official+codex · reviewed · Jun 3, 2026 description in en

Description

Local llama.cpp inference can use HIP and ROCm acceleration through Python bindings on supported GPUs. AI developers use this variant for AMD-backed local model workloads. Driver versions, GPU memory, model provenance, and generated output need validation.

Permissions

Permissions not analysed for this source yet.