REPOMIND

Open-source repo-scale coding agent on AMD MI300X.

Ingest a git repository (up to 256K tokens, FP8) on a single GPU and reason across the whole codebase with multi-step tool use.

📦 GitHub: SRKRZ23/repomind 🏆 Built for the AMD Developer Hackathon 2026

Why MI300X?

Qwen3-Coder-Next-FP8 weights ≈ 80 GB
256K KV cache @ FP8 ≈ 38 GB
- activations ≈ 25 GB → ~143 GB total on a single GPU
NVIDIA H100 80GB physically OOMs. AMD MI300X 192GB just runs it.

About this Space

This is the frontend demo. Backend defaults to the mock LLM so the Space runs on CPU-basic without burning GPU credits. Switch to vllm and provide a base URL once the MI300X endpoint is live.