vLLM says it delivered 7.8x or more the throughput of GB200 on SemiAnalysis AgentX, serving MiniMax M3 on Vera Rubin NVL72 at matched interactivity. In MLPerf Inference v6.1, vLLM with Dynamo reached up to 3.7x the throughput of GB300 NVL72 on Qwen3-VL-235B-A22B.
Part of a thread · earlier post
The numbers come from two benchmarks. On @SemiAnalysis_ AgentX, vLLM serving MiniMax M3 on Vera Rubin NVL72 delivers 7.8x+ the throughput of GB200 at matched interactivity. In MLPerf Inference v6.1, vLLM with Dynamo reached up to 3.7x the throughput of GB300 NVL72 on Qwen3-VL-235B-A22B.
🧵 2/5
Source: vLLM · x.comPublished · added here
