Statements (28)
| Predicate | Object |
|---|---|
| gptkbp:instanceOf |
gptkb:graphics_card
|
| gptkbp:architecture |
gptkb:Hopper
|
| gptkbp:connects |
gptkb:NVLink
gptkb:PCIe_Gen5 |
| gptkbp:formFactor |
gptkb:PCIe
gptkb:SXM |
| https://www.w3.org/2000/01/rdf-schema#label |
NVIDIA H200
|
| gptkbp:manufacturer |
gptkb:NVIDIA
|
| gptkbp:memoryType |
HBM3e
|
| gptkbp:peakMemoryBandwidth |
4.8 TB/s
|
| gptkbp:predecessor |
gptkb:NVIDIA_H100
|
| gptkbp:processNode |
gptkb:TSMC_4N
|
| gptkbp:RAM |
141 GB
|
| gptkbp:releaseDate |
2024
|
| gptkbp:successor |
gptkb:NVIDIA_H100
|
| gptkbp:supports |
gptkb:Tensor_Cores
BF16 FP16 FP8 INT8 |
| gptkbp:targetMarket |
data centers
AI inference AI training |
| gptkbp:usedFor |
high performance computing
large language models |
| gptkbp:bfsParent |
gptkb:NVIDIA_HGX_systems
gptkb:NVIDIA_Data_Center_GPU_family |
| gptkbp:bfsLayer |
8
|