Inference Latency and Throughput on CNN/DM (Summarization)
3.58Speedup
TALON
Updated 4d ago
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
2026.01 | 3.58 | - | 7.2 | |
2026.01 | 3.43 | - | 6.93 | |
2026.01 | 3.3 | - | 5.28 | |
2026.01 | 3.22 | - | 6.91 | |
2026.01 | 3.14 | - | 4.75 | |
2026.01 | 3.06 | - | 5.46 | |
2026.01 | 2.89 | - | 5.03 | |
2026.01 | 2.3 | - | 3.2 | |
2026.01 | 1.95 | - | 3.27 | |
2026.01 | 1.86 | - | 2.82 | |
2026.01 | 1.72 | - | 2.54 | |
2026.02 | 1.71 | 14.5 | - | |
2026.02 | 1.7 | 14.4 | - | |
2026.01 | 1.57 | - | 2.57 | |
2026.01 | 1.56 | - | 2.09 | |
2026.01 | 1.41 | - | 2.63 | |
2026.02 | 1.4 | 21.51 | - | |
2026.02 | 1.39 | 23.77 | - | |
2026.02 | 1.38 | 23.55 | - | |
2026.02 | 1.34 | 20.55 | - | |
2026.02 | 1.34 | 11.36 | - | |
2026.02 | 1.3 | 22.27 | - | |
2026.02 | 1.2 | 18.52 | - | |
2026.02 | 1.15 | 17.64 | - | |
2026.02 | 1.14 | 9.62 | - | |
2026.02 | 1.09 | 16.7 | - | |
2026.02 | 1.08 | 18.21 | - | |
2026.02 | 1.06 | 18.5 | - | |
2026.02 | 1.01 | 8.56 | - | |
2026.02 | 1 | 17.11 | - | |
2026.02 | 1 | 15.37 | - | |
2026.02 | 1 | 8.46 | - |