Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Inference Speedup on BERT base
Loading...
21.5
Speedup
TRT FP16
0.18
5.715
11.25
16.785
Mar 30, 2026
Speedup
Updated 19d ago
Evaluation Results
Method
Method
Links
Speedup
TRT FP16
Precision=FP16, Approa...
2026.03
21.5
TRT FP32
Precision=FP32, Approa...
2026.03
10.8
FasterTF
Precision=FP16, Approa...
2026.03
4
FastFormers
Precision=FP32, Approa...
2026.03
1.8
PyTorch GPU
Precision=FP32, Approa...
2026.03
1
Feedback
Search any
task
Search any
task