AMD MI355X vLLM Beats Nvidia B200 on Kimi K2.5 Inference

marksaroufim · x · 2026-08-02

Recent benchmarks from SemiAnalysis reveal that AMD's MI355X has outperformed Nvidia's B200 in vLLM inference running Kimi K2.5 (sharing the same architecture as xAI Cursor Composer 2.5).

This performance leap is largely attributed to upstream AMD kernels optimized by the @GPUMODE community, highlighting the growing impact of open-source collaboration in maximizing hardware inference efficiency.

Original post →

More from Infra

Infra channel →