Setting up local LLMs on AMD GPUs can be tricky. I built two open-source zero-dependency tools to make it seamless:🛠️ RO...

Setting up local LLMs on AMD GPUs can be tricky. I built two open-source zero-dependency tools to make it seamless:🛠️ ROCmFix: Auto-detects AMD GPUs and configures HSA_OVERRIDE_GFX_VERSION on Windows & Linux.📊 InferBench: Benchmarks local LLM APIs (Ollama / LM Studio) comparing Vulkan vs HIP with warm-up passes and cold VRAM resets.🔗 https://github.com/xanpavle/rocmfix🔗 https://github.com/xanpavle/inferbench#LocalLLM #ROCm #AMD #OpenSource #AI