Semantic Textual Similarity on STS-B (Performance Evaluation)
22.63Latency (ms)flashsvd15
Evaluation results
| Method | Links | |||
|---|---|---|---|---|
| flashsvd15Backend=flashsvd15, Precision=bf16, Sequence Length=512, Batch Size=32, Input Type=synthetic, Model=SVD-compressed BERT2026.05 | 22.63 | 1,414.2 | 343.9 | |
| sdpaBackend=sdpa, Precision=bf16, Sequence Length=512, Batch Size=32, Input Type=synthetic, Model=SVD-compressed BERT2026.05 | 25.5 | 1,254.8 | 605.2 | |
| flashsvdBackend=flashsvd, Precision=bf16, Sequence Length=512, Batch Size=32, Input Type=synthetic, Model=SVD-compressed BERT2026.05 | 44.86 | 713.4 | 341.4 | |
| naiveBackend=naive, Precision=bf16, Sequence Length=512, Batch Size=32, Input Type=synthetic, Model=SVD-compressed BERT2026.05 | 51.41 | 622.4 | 989.2 |