解决方案
品牌 | 规格 | 算力 |
英伟达 NVIDIA |
HGX H20 | FP32 44 TFLOPS FP16 148 TFLOPS INT8 Tensor Core 296 TFLOPS |
英伟达 NVIDIA |
L20 Pcle | FP32 59.8 TFLOPS FP16 119.5 TFLOPS INT8 Tensor Core 239 TFLOPS |
英伟达 NVIDIA |
L20 Pcle | FP32 24.1 TFLOPS FP16 96.5 TFLOPS INT8 Tensor Core 193 TFLOPS |
英伟达 NVIDIA |
H100 SXM | FP32 67 TFLOPS FP16 Tensor Core 1,979 teraFLOPS2 INT8 Tensor Core 3,958 TOPS2 |
英伟达 NVIDIA |
H100 PCIe | FP32 51 TFLOPS FP16 Tensor Core 1513 teraFLOPS2 INT8 Tensor Core 3026 TOPS2 |
英伟达 NVIDIA |
H100 NVL | FP32 134 TFLOPS FP16 Tensor Core 6958 teraFLOPS2 INT8 Tensor Core 7916 TOPS2 |
英伟达 NVIDIA |
H800 SXM | FP32 67 TFLOPS FP16 Tensor Core 1979 TFLOP INT8 Tensor Core 3958 TFLOPS |
英伟达 NVIDIA |
H800 PCle | FP32 51 TFLOPS FP16 Tensor Core 1513 TFLOP INT8 Tensor Core 3026 TFLOPS |
英伟达 NVIDIA |
A100 80GB Pcle | FP32 19.5 TFLOPS FP16 Tensor Core 312 TFLOPS|624 TFLOPS* INT8 Tensor Core 624 TOPS| 1248 TOPS* |
英伟达 NVIDIA |
A100 80GB SXM | FP32 19.5 TFLOPS INT8 Tensor Core 624 TOPS| 1248 TOPS* FP16 Tensor Core 312 TFLOPS|624 TFLOPS* |
品牌 | 规格 | 算力 |
寒武纪 | MLU290-M5 | 512 TOPS (INT8) 256 TOPS (INTI6) 64 TOPS (CINT32) |
寒武纪 | MLU370-X8 | 256 TOPS (INT8) I28 TOPS (INTI6) 96 TFLOPS (FPI6) 96 TFLOPS (BFI6) 24 TFLOPS (FP32) |
寒武纪 | MLU370-X4 | 256 TOPS (INT8) I28 TOPS (INTI6) 96 TFLOPS (FPI6) 96 TFLOPS (BFI6) 24 TFLOPS (FP32) |
寒武纪 | MLU370-S4/S8 | 192 TOPS (INT8) 96 TOPS (INT16) 72 TFLOPS (FP16) 72 TFLOPS (BF16) 18 TFLOPS (FP32) |
燧原 | 云燧i20 | 256 TOPS (INT8) 128 TFLOPS (FP16) 32 TFLOPS (FP32) |
燧原 | 云燧i10 | 470.4 TFLOPS (INT8) 70.4 TFLOPS (FP16) 17.6 TFLOPS (FP32) |
燧原 | 云燧T21 | 256 TOPS (INT8) 128 TFLOPS (FP16) 32 TFLOPS (FP32) |
燧原 | 云燧T20 | 256 TOPS (INT8) 128 TFLOPS (FP16) 32 TFLOPS (FP32) |