Statements (51)
| Predicate | Object |
|---|---|
| gptkbp:instanceOf |
gptkb:server
|
| gptkbp:announced |
2017
|
| gptkbp:developedBy |
gptkb:Nvidia
|
| gptkbp:features |
scalable architecture
high bandwidth memory multi-GPU support liquid cooling (optional) |
| gptkbp:formFactor |
rack-mounted
|
| https://www.w3.org/2000/01/rdf-schema#label |
Nvidia HGX systems
|
| gptkbp:includes |
gptkb:Nvidia_A100
gptkb:Nvidia_H100 gptkb:Nvidia_V100 |
| gptkbp:supports |
gptkb:CUDA
gptkb:NVLink gptkb:PCIe gptkb:Nvidia_NVSwitch gptkb:Tensor_Cores BF16 FP16 INT8 Nvidia GPUs FP32 FP64 AI frameworks |
| gptkbp:usedBy |
gptkb:Google_Cloud_Platform
gptkb:OpenAI gptkb:Amazon_Web_Services gptkb:Meta gptkb:Microsoft_Azure |
| gptkbp:usedFor |
gptkb:artificial_intelligence
gptkb:simulation climate modeling genomics medical research natural language processing scientific computing supercomputing data analytics drug discovery financial modeling high performance computing enterprise AI large language models deep learning inference deep learning training autonomous vehicles development cloud AI services |
| gptkbp:usedIn |
cloud computing
data centers |
| gptkbp:bfsParent |
gptkb:Nvidia_NVSwitch
|
| gptkbp:bfsLayer |
6
|