Open wangjio opened 2 years ago
Hi,I am a novice in Transformer. In function 'predict()', I noticed that the time consuming of transformer decoder in for loop is not stable. The average time of one loop is about 2ms. But there always exists some peak. Do you have any idea? Thanks!
Hi,I am a novice in Transformer. In function 'predict()', I noticed that the time consuming of transformer decoder in for loop is not stable. The average time of one loop is about 2ms. But there always exists some peak. Do you have any idea? Thanks!