wafer(@wafer_ai):🚨 BREAKING: these engineers figured out how to serve Kimi K3 on @AMD MI355X at 952 tok/s/node and 118 tok/s single stream! this crushes B200 by 3.8x in aggregate throughput/node and 1.3x in single stream decode + beats B300 on performance per dollar (48 vs 33 tok/s/$) See how in the thread.

wafer

@wafer_ai

Inference that Keeps Getting Better Wafer learns how your workload behaves and continuously optimizes the serving stack for better performance & reliability

参加 June 2025

10 フォロー中 11.5K ファン

wafer@wafer_ai

2026.08.01 18:58

🚨 BREAKING: these engineers figured out how to serve Kimi K3 on @AMD MI355X at 952 tok/s/node and 118 tok/s single stream! this crushes B200 by 3.8x in aggregate throughput/node and 1.3x in single stream decode + beats B300 on performance per dollar (48 vs 33 tok/s/$) See how in the thread.