AMD MI300X에서 ROCm으로 파인튜닝된 MedQA 임상 AI
새로운 임상 AI 모델이 ROCm을 사용해 AMD 하드웨어만으로 파인튜닝되어 CUDA 없이도 HuggingFace 생태계가 작동함을 입증했습니다. Qwen3-1.7B 기반 모델은 2,000개 샘플로 5분 만에 학습되었습니다.
A project named MedQA successfully fine-tuned a clinical question-answering model using only AMD hardware and the ROCm software stack. Built on a single AMD Instinct MI300X with 192 GB of HBM3 memory, the pipeline fine-tuned Qwen3-1.7B using LoRA without any CUDA dependencies or code changes. Training on 2,000 MedMCQA samples took approximately 5 minutes, utilizing full fp16 precision to avoid quantization. The resulting model generates answers and clinical explanations for medical multiple-choice questions, validating that the HuggingFace ecosystem—including Transformers, PEFT, and TRL—operates seamlessly on ROCm.