Language Model Inference on Sequence Bucket Short
39.26Latency (ms)COREY
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
| COREYPrecision=FP162026.04 | 39.26 | 38.3 | 2,120 | |
| Static FusionPrecision=FP162026.04 | 42.61 | 35.3 | 2,319 | |
| No FusionPrecision=FP162026.04 | 52.06 | 28.9 | 2,805 |
| Method | Links | |||
|---|---|---|---|---|
| COREYPrecision=FP162026.04 | 39.26 | 38.3 | 2,120 | |
| Static FusionPrecision=FP162026.04 | 42.61 | 35.3 | 2,319 | |
| No FusionPrecision=FP162026.04 | 52.06 | 28.9 | 2,805 |