ENTITY PROFILE / 实体档案
NVIDIA GB300 NVL72 systems
NVIDIA DSX MaxLPS enabled 37% more GPUs and nearly 50% higher aggregate inference throughput within NVIDIA GB300 NVL72 systems Nemotron 3.5 Transcribe was fine‑tuned for 14 GPU hours on a single Nvidia GB300· Graphiti 生成的实体摘要
RELATIONS
4关系CURRENT
4当前有效EVENTS
3相关事件REPORTS
3来源报道暂无可公开的邻近关系
按需展开实体的全部已公开关系，保留探索过的节点与连线。
关系变化
按生效时间- NVIDIA Nemotron 3.5 TranscribeTRAINED ONNVIDIA GB300 NVL72 systems
Nemotron 3.5 Transcribe was fine‑tuned for 14 GPU hours on a single Nvidia GB300
- A4X Max instancesUSESNVIDIA GB300 NVL72 systems
A4X Max instances use NVIDIA GB300 NVL72
- A5X instancesINCLUDESNVIDIA GB300 NVL72 systems
A5X instances include NVIDIA Vera Rubin NVL72
- NVIDIA DSX MaxLPSINCREASED INFERENCE THROUGHPUTNVIDIA GB300 NVL72 systems
NVIDIA DSX MaxLPS enabled 37% more GPUs and nearly 50% higher aggregate inference throughput within NVIDIA GB300 NVL72 systems
关系是 Graphiti 从报道中提取的事实陈述，不是原文引述；失效时间表示后来的报道显示这条关系已不成立。