|
Détails sur le produit:
|
| FP64: | 34 teraFLOPS | Noyau du tenseur FP64: | 67 teraFLOPS |
|---|---|---|---|
| FP32: | 67 teraFLOPS | Noyau du tenseur TF32: | 989 téraFLOPS |
| Mémoire de GPU: | 80GB | Largeur de bande de mémoire de GPU: | 3.35 TB/s |
| Décodeurs: | 7 NVDEC 7 JPEG | Puissance thermique maximum de conception (TDP): | Jusqu'à 700 W (configurable) |
| GPU multi-instances: | Jusqu'à 7 MIG à 10 Go chacun | Facteur de forme: | SXM |
| Mettre en évidence: | 80GB GPU Memory NVIDIA H100 SXM GPU,SXM Form Factor H100 SXM Tensor Core GPU,700W Configurable TDP NVIDIA H100 SXM GPU |
||
H100 features fourth-generation Tensor Cores and a Transformer Engine with FP8 precision that provides up to 4X faster training over the prior generation for GPT-3 (175B) models. For high-performance computing (HPC) applications, H100 triples the floating-point operations per second (FLOPS) of double-precision Tensor Cores, delivering 60 teraflops of FP64 computing for HPC while also featuring dynamic programming (DPX) instructions to deliver up to 7X higher performance. With
Personne à contacter: Alisa CC
Téléphone: +86 18710168043