Inference Efficiency on Model Profiling
15.9Total GEMM Latency (ms)
ESPACE
Updated 3d ago
Evaluation Results
| Method | Links | ||
|---|---|---|---|
2024.10 | 15.9 | 31.7 | |
2024.10 | 20.6 | 36.1 | |
2024.10 | 24.2 | 39.8 | |
2024.10 | 76.8 | 122 | |
2024.10 | 110 | 155 | |
2024.10 | 113 | 266 | |
2024.10 | 136 | 186 | |
2024.10 | 169 | 322 | |
2024.10 | 181 | 261 | |
2024.10 | 210 | 368 | |
2024.10 | 210 | 368 | |
2024.10 | 223 | 545 | |
2024.10 | 229 | 313 | |
2024.10 | 259 | 447 | |
2024.10 | 324 | 655 | |
2024.10 | 336 | 562 | |
2024.10 | 354 | 457 | |
2024.10 | 406 | 643 | |
2024.10 | 414 | 741 |