Language Model Inference on Sequence Bucket Medium
52.88Latency (ms)COREY
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
| COREYPrecision=FP162026.04 | 52.88 | 114.1 | 717 | |
| Static FusionPrecision=FP162026.04 | 56.75 | 106.3 | 778 | |
| No FusionPrecision=FP162026.04 | 68.87 | 87.6 | 940 |
| Method | Links | |||
|---|---|---|---|---|
| COREYPrecision=FP162026.04 | 52.88 | 114.1 | 717 | |
| Static FusionPrecision=FP162026.04 | 56.75 | 106.3 | 778 | |
| No FusionPrecision=FP162026.04 | 68.87 | 87.6 | 940 |