List your company

Inference Latency on Synthetic Sequence length 256

0.009Original Latency (s)BERT
0.0088760.0097130.010550.011387May 14, 2026

Evaluation results

MethodLinks
BERTHardware=A100, Batch Size=2, Sequence Length=2562026.050.009——
CBWCModel=BERT, Hardware=A100, Batch Size=2, Sequence Length=2562026.050.0090.00872.79
GPT-2Hardware=A100, Batch Size=2, Sequence Length=2562026.050.0093——
CBWCModel=GPT-2, Hardware=A100, Batch Size=2, Sequence Length=2562026.050.00930.00894.22
OPTHardware=A100, Batch Size=2, Sequence Length=2562026.050.0094——
CBWCModel=OPT, Hardware=A100, Batch Size=2, Sequence Length=2562026.050.00940.00895.85
BERTHardware=V100, Batch Size=2, Sequence Length=2562026.050.0116——
CBWCModel=BERT, Hardware=V100, Batch Size=2, Sequence Length=2562026.050.01160.01113.9
OPTHardware=V100, Batch Size=2, Sequence Length=2562026.050.0119——
CBWCModel=OPT, Hardware=V100, Batch Size=2, Sequence Length=2562026.050.01190.01162.53
GPT-2Hardware=V100, Batch Size=2, Sequence Length=2562026.050.0121——
CBWCModel=GPT-2, Hardware=V100, Batch Size=2, Sequence Length=2562026.050.01210.01173.57