vLLM Benchmarks Show Rubin NVL72 Delivering 10.2x GB300 Throughput

The vLLM team announced Day-0 support for MiniMax-M3.1-Flash across NVIDIA Blackwell, Rubin and AMD MI350 GPUs, with throughput on Vera Rubin NVL72 reaching 10.2x that of GB300 in SemiAnalysis AgentX benchmarks.

2026-11-12 ~ 2026-11-12 · 2 related posts

• vLLM benchmarks MiniMax-M3.1-Flash on Vera Rubin NVL72: 10.2x per-chip throughput vs GB300 — vllm_project · 2026-11-12
• vLLM ships Day-0 support for MiniMax-M3.1-Flash with 10.2x throughput on Rubin NVL72 — vllm_project · 2026-11-12