DeepSeek V4.1 Flash on Vera Rubin NVL72: 63-93x per-chip throughput vs GB300 in vLLM benchmarks

vllm_project · x · 2026-11-17

vLLM project published the first DeepSeek V4.1 Flash (552B, FP4) inference results on NVIDIA Vera Rubin NVL72, powered by Dynamo + vLLM on SemiAnalysis' AgentX benchmark. Compared to GB300 NVL72 with the same stack, InferenceX's perf ruler shows 63.4× total token throughput per chip at 400 tok/s/user and 93.3× at 600 tok/s/user.

Original post →

More from Infra

Infra channel →