Language Model Inference on Sequence Bucket Long
69.58Latency (ms)COREY
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
| COREYPrecision=FP162026.04 | 69.58 | 350.3 | 241 | |
| Static FusionPrecision=FP162026.04 | 73.61 | 328.3 | 254 | |
| No FusionPrecision=FP162026.04 | 88.54 | 273.1 | 305 |
| Method | Links | |||
|---|---|---|---|---|
| COREYPrecision=FP162026.04 | 69.58 | 350.3 | 241 | |
| Static FusionPrecision=FP162026.04 | 73.61 | 328.3 | 254 | |
| No FusionPrecision=FP162026.04 | 88.54 | 273.1 | 305 |