Views
No views yet
| TensorRT INT8+FP32 | torch FP16 | |
|---|---|---|
| Lambada Acc | 72.11% | 71.43% |
| Input sequance length | Number of generated tokens | TensorRT INT8+FP32 ms | torch FP16 ms | Acceleration |
|---|---|---|---|---|
| 64 | 64 | 462 | 1190 | 2.58 |
| 64 | 128 | 920 | 2360 | 2.54 |
| 64 | 256 | 1890 | 4710 | 2.54 |
git clone https://github.com/ENOT-AutoDL/ENOT-transformers