Remove demo script from public repository

Update DEMO_SCRIPT with polished presentation text

Expand WMMA intrinsic mappings for accurate risk heatmap

Fix Dockerfile heatmap risk level

Merge remote-tracking branch 'huggingface/main'

Fix AMD Readiness Score and WMMA Heatmap

Update README.md

fix: use port 7860 for Hugging Face Docker Spaces

fix: remove Hugging Face metadata table from GitHub README

chore: remove demo script from repository tracking

fix: add Hugging Face Spaces YAML metadata

benchmark: MI300X results — 603 TFLOPS FP16, 4.6 TB/s bandwidth

fix: compatibility with PyTorch 2.9 (total_mem -> total_memory)

docs: update demo script to humorous war-story format

docs: highlight AST-level analysis in README pipeline

feat: AST-level Python analysis + MI300X benchmark suite

polish: premium UI upgrades for hackathon demo

feat(ui): add presentation components recommended by judges

feat: 9-agent pipeline with hardware-aware analysis, drift detection, build copilot

chore: Clean up demo script and enhance README with live URL and Mermaid diagram

feat: Add AMD GPU fine-tuning pipeline (QLoRA on CodeLlama via ROCm)

Initial commit for AMD Developer Hackathon: Multi-Agent ROCm Migration Engine