1M Tokens/s: Scaling Qwen 3.5 27B on 96 B200 GPUs with vLLM #1 Post by m4r1k » Fri, Mar 27, 2026, 1:54 PM UTC 1M Tokens/s: Scaling Qwen 3.5 27B on 96 B200 GPUs with vLLMmedium.com