AMD · Anthropic · OpenAI · GitHub · Hugging Face
MachinaCheck: Building a Multi-Agent CNC Manufacturability System on AMD MI300X
Compiled by KHAO Editorial — aggregated from 1 outlet. See llms.txt for citation guidance.
★ Tier-1 Source
Walk into any small CNC machine shop and ask the manager how they decide whether to accept a customer job.
Key facts
- Built by Syed Muhammad Sarmad and Sabari Doss R at the AMD Developer Hackathon, May 2026
- With 192GB of HBM3 VRAM and 5.3 TB/s of memory bandwidth, they run Qwen 2.5 7B Instruct entirely on-premise
- For a busy shop receiving 10 to 20 RFQs per week, that is 5 to 20 hours of skilled manager time spent on feasibility analysis alone
- Running Qwen 2.5 7B on AMD MI300X via ROCm and vLLM was straightforward
Summary
The answer is almost always the same: they print the drawing, read every dimension by hand, walk around the shop checking which tools are available, estimate whether their machines can hold the required tolerances, and write notes on a clipboard. Sometimes they get it wrong. They accept a job, start production, and discover halfway through that they don't have the right tap or that their mill cannot hold the tolerance on a critical feature. MachinaCheck is a multi-agent AI system. Before explaining the architecture, this point deserves its own section because it is not a technical choice, it is a business requirement.