NVIDIA Vera Rubin NVL72 首批基准成绩公布
NVIDIA 新一代 Vera Rubin NVL72 的跑分出来了，跑 DeepSeek V4 Pro 每兆瓦吞吐量是上一代的 5.7 倍，还刷出 906 tok/s 的单用户最快速度。
Artificial Analysis 的 AA-AgentPerf 基准收录了 NVIDIA Vera Rubin NVL72 的首批成绩，该系统搭载 72 块 Rubin GPU 和 36 颗 Vera CPU。在 DeepSeek V4 Pro 上，其每兆瓦吞吐量达到前代 GB300 NVL72 的约 5.7 倍，在 DeepSeek V4.1 Flash 上约 5.4 倍，GLM-5.2 和 Kimi K3 上分别为 3.0 倍和 2.8 倍。在高速输出场景下优势更明显：DeepSeek V4 Pro 上每用户速度从约 120 提升到 165 tok/s 时，GB300 损失 81% 的吞吐量，Vera Rubin 只损失 16%。Vera Rubin 还创下 DeepSeek V4.1 Flash 906 tok/s 的最快单用户速度纪录。所有结果由 NVIDIA 提交，使用 TensorRT-LLM、vLLM 与 NVIDIA Dynamo 运行。
Initial results for NVIDIA's Vera Rubin NVL72 are now live on AA-AgentPerf, with up to ~5.7x the total throughput per megawatt of its predecessor GB300 NVL72 on DeepSeek V4 Pro, ~5.4x on DeepSeek V4.1 Flash, ~3.0x on GLM-5.2 and ~2.8x on Kimi K3
Vera Rubin is NVIDIA's successor to Blackwell, and Vera Rubin NVL72 is its rack-scale system, with 72 Rubin GPUs and 36 Vera CPUs. Each Rubin GPU has the same 288 GB of memory as Blackwell Ultra, but 2.4x the memory bandwidth, 1.7x the NVLink bandwidth and 2.3x the dense NVFP4 compute. NVIDIA submitted every Vera Rubin result, running TensorRT-LLM and vLLM with NVIDIA Dynamo
AA-AgentPerf is our agentic inference performance benchmark. It replays real agentic coding sessions, including long cached contexts and tool-call delays, to give a realistic measure of inference performance in day-to-day agentic workloads. We measure total system throughput per megawatt of measured GPU power, and per-agent output speed (p25 across requests) at varying concurrency levels, to show the trade-off between system utilization and individual user experience
Initial results:
➤ Vera Rubin's lead is largest at faster per-user speeds, where GB300's throughput falls away. On DeepSeek V4 Pro, going from ~120 to ~165 tok/s per user costs GB300 81% of its throughput per MW, compared to 16% for Vera Rubin
➤ At peak throughput the two are closer, with Vera Rubin at 272M tokens/s per MW on DeepSeek V4 Pro vs 239M for GB300 (1.14x), 571M vs 395M on DeepSeek V4.1 Flash (1.45x), 272M vs 201M on GLM-5.2 (1.35x) and 70M vs 56M on Kimi K3 (1.26x). We expect the gap between the systems to widen as Vera Rubin kernels and other serving software are optimized
➤ Vera Rubin sets the fastest per-user speeds on our leaderboard for DeepSeek V4.1 Flash (906 tok/s, the fastest result for any model), GLM-5.2 (408 tok/s) and Kimi K3 (255 tok/s)
Congratulations @nvidia on the strong results!
Read the full analysis: https://t.co/gxAXCrVEh2
