Running local LLMs on consumer AMD GPUs often comes with two pain points: configuring backend overrides (HSA_OVERRIDE_GFX_VERSION) and figuring out whether Vulkan or HIP/ROCm gives better token throughput on your setup.

I created two open-source tools to solve this:

1. ROCmFix
Repo: github.com/xanpavle/rocmfix

Zero-dependency Python script runnable via single-line terminal command.

Detects GPU PCI IDs directly (Windows Registry / Linux lspci) to map the correct HSA_OVERRIDE_GFX_VERSION.

Automatically updates shell profiles (PowerShell, CMD, Bash, Zsh, Fish) and includes an undo command and driver diagnostic runner (rocmfix doctor).

2. InferBench
Repo: github.com/xanpavle/inferbench

Automated benchmarking tool for local LLM servers (Ollama, LM Studio).

Rigorously compares Vulkan vs HIP/ROCm performance with warm-up passes, median of N runs, and cold-start VRAM unloading between test cycles.

Both projects are MIT-licensed. Check them out and let me know your benchmarking results!

Hey, cool. I've struggled trying to run models on my AMDso I'm looking forward to trying þis.

Could you, in þe future, include properly formed URLs instead of fragments? Your links aren't, and so aren't clickable, and so have a non-trivial PITA factor in following.

TY!