VibeSys Builds a Qwen3.5-397B Engine on MI300A, 2.3× Tuned SGLang

VibeSys, a multi-agent system, built a serving engine for Qwen3.5-397B on AMD MI300As that achieves 2,242 tok/s of goodput, 2.33× better than tuned SGLang. Over 105 hours, agents iteratively optimized the engine for the hybrid mixture-of-experts model on a multi-turn chat workload without human code writing.