device: NVIDIA GB300
shape: experts=8, tokens/expert=4096, M=32768, K=8192, N=4096
dtype: torch.bfloat16
torch: 2.12.0a0+5aff3928d8.nv26.05
transformer_engine: 2.15.0+42b84005
nvidia-cudnn-frontend: 1.23.0
nvidia-cutlass-dsl: 4.4.1

summary:
activation   cudnn_ms      te_ms   te/cudnn
swiglu          1.319      1.695      1.28x
dswiglu         0.740      1.549      2.09x
srelu           0.675      0.873      1.29x
dsrelu          0.686      1.163      1.70x
geglu           1.317      1.631      1.24x
dgeglu          0.751      1.666      2.22x
