|
Datos del producto:
|
| FP64: | 34 teraFLOPS | Base del tensor FP64: | 67 teraFLOPS |
|---|---|---|---|
| FP32: | 67 teraFLOPS | Base del tensor TF32: | 989 teraFLOPS |
| Memoria de GPU: | 80GB | Ancho de banda de la memoria de GPU: | 3.35 TB/s |
| Decodificadores: | 7 NVDEC 7 JPEG | Poder termal máximo del diseño (TDP): | Hasta 700W (configurable) |
| GPU de instancias múltiples: | Hasta 7 MIG de 10 GB cada uno | Factor de forma: | SXM |
| Resaltar: | 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
Persona de Contacto: Alisa CC
Teléfono: +86 18710168043