AMD Engineers Port 50 Models to Client GPUs in Three Days Using HRX Loom and AI Agents
An internal AMD experiment shows that combining HRX Loom with AI agents can reduce model porting time to days, yielding up to 2.1x performance gains.
Engineers Jeremy Fowers and Ben Vanik at U.S. semiconductor company AMD led an internal experiment leveraging the newly released ROCm HRX Loom v0.1 software stack and an AI agent workflow to port 50 popular Hugging Face models across 18 architectures to AMD client GPUs in approximately three to four days.
The experiment aimed to demonstrate the potential of accelerating the adaptation of new and niche models to AMD hardware through HRX Loom and agentic AI. According to AMD's report, the process achieved a medium speed-up of 1.5 to 2.1 times for 32K token prompt processing compared to Llama.cpp's ROCm backend, and a 1.9 times speed-up compared to its Vulkan backend.
HRX Loom remains an experimental project supporting CPU, GPU, and NPU execution. These results highlight AMD's effort to narrow the compatibility gap between its software ecosystem and mainstream open-source models via automated toolchains, though the specific performance figures have not been independently verified.