Encrypted LLM Inference Execution Time on 128 token prompt
2.7Latency (s)
PowerSoftmax
Updated 2mo ago
Evaluation Results
| Method | Links | |
|---|---|---|
2024.10 | 2.7 | |
2024.10 | 3.6 | |
2024.10 | 7.42 | |
2024.10 | 11.1 | |
2024.10 | 16.6 | |
2024.10 | 19.4 | |
2024.10 | 42.1 | |
2024.10 | 46.1 | |
2024.10 | 84.05 | |
2025.12 | 134 | |
2025.12 | 152 | |
2025.12 | 215 | |
2025.12 | 253 | |
2025.12 | 295 | |
2025.12 | 341 | |
2025.12 | 346 | |
2025.12 | 385 | |
2025.12 | 575 | |
2025.12 | 580 | |
2025.12 | 675 | |
2025.12 | 698 | |
2025.12 | 13,271 |