LecturaInvestigaciónRadarMarco de inversión
Iniciar sesión / Registrarse
← Volver a la lectura
NoticiasTema · Vera RubinMaterial2 min de lecturaEditorial de DisconfirmAI

NVIDIA Publishes Provisional MLPerf Results: Vera Rubin Platform Shows >10x Energy Efficiency Gain Over GB300 in Agentic Inference

NVIDIA released preliminary MLPerf Endpoints v1.0 benchmark data for its Vera Rubin NVL72 platform, indicating over 10x higher throughput per kilowatt compared to GB300 under agentic workloads.

2026-11-17 00:00 GMT+8

NVIDIA published preliminary results for its latest AI superchip platform, the Vera Rubin NVL72, in the MLPerf Endpoints v1.0 benchmark suite on November 16, 2026. The data indicates that at a shared minimum end-to-end interactivity of 50 tokens per second per user, the Vera Rubin NVL72 delivers over 10 times the throughput per kilowatt of the previous generation GB300 NVL72. This result highlights the new platform's energy efficiency advantages when handling agentic workloads involving multi-turn conversations and tool calls.

The tests covered three open-source models: Kimi K3, DeepSeek-V4.1-Flash, and Qwen3.6-35B-A3B. At matched query concurrency, the Vera Rubin NVL72 achieved 3x to 5x higher end-to-end interactivity. Conversely, at fixed interactivity thresholds, it demonstrated 5x to 10x higher throughput per kilowatt. For instance, running Kimi K3 at 1,024 concurrent queries, the Vera Rubin system achieved 41,414 tokens/sec with 100.89 kW power consumption, whereas the GB300 system reached only 13,905.8 tokens/sec at 60 kW under the same concurrency.

NVIDIA attributes these gains to the Rubin GPU architecture's HBM4 memory, Tensor Cores, and sixth-generation NVLink, combined with context-aware serving techniques like prefix caching, state reuse, and Dynamo routing. These optimizations reduce redundant computation and balance load. Additionally, model-specific execution optimizations, such as DeepSeek's MegaMoE kernel and Qwen's multi-token prediction with Tensor Core verification, help minimize data movement and sequential decoding steps.

Iniciar sesión / Registrarse
LecturaInvestigaciónRadarMarco de inversión

It is crucial to note that these results are marked as "provisional" and have not yet undergone final peer review and verification by the MLCommons Association, meaning they are subject to change. The GB300 results used for comparison have been verified by MLCommons. For readers tracking AI infrastructure efficiency, this data offers an early reference for new hardware performance under standardized agentic loads, though real-world production metrics await independent validation.

Fuentes

  • developer.nvidia.comNVIDIA Technical Blog↗
Tema

Vera Rubin

【背景】英伟达(NVIDIA)于2026年11月16日首次公布其下一代AI超级计算机平台Vera Rubin的MLPerf基准测试结果。数据显示,Vera Rubin NVL72系统在智能体推理(Agentic Inference)任务中,…

3 pasos2 piezasActualizado 2026-11-20 02:57

Cómo llegó hasta aquí

  1. 2026-11-16英伟达官方博客发布Vera Rubin平台在MLPerf Training v6.1和Endpoints v1.0中的初步基准数据,宣称智能体推理能效比GB300提升超10倍。blogs.nvidia.com ↗
  2. 2026-11-17英伟达技术博客详细解读Vera Rubin NVL72在Kimi K3等模型上的具体测试参数,确认数据为“Provisional”(暂定/待验证)状态。developer.nvidia.com ↗
  3. 2026-11-18第三方机构AGI Tracker发布分析报告,指出“10倍”能效提升基于未验证数据,并计算出在更严格条件下实际提升约为3倍。agitracker.io ↗

Lo que aún está pendiente

  • MLCommons协会何时完成对Vera Rubin初步结果的正式验证?
  • 在已验证的GB300数据与不同并发设置下,Vera Rubin的实际能效优势区间是多少?
  • 除英伟达外,其他云服务商(如Google Cloud, Azure)是否会在后续提交Vera Rubin的独立验证数据?

También en este hilo

  • NVIDIA Vera Rubin Debuts in MLPerf Benchmarks, Claims Over 10x Agentic Inference Efficiency Gain2026-11-17
Leer el tema completo →
Continuar investigando →