计算时间

17:46.738 10个文件的总执行时间 来自所有图库

示例

时间

内存 (MB)

融合注意力 (../python/tutorials/06-fused-attention.py)

13:09.208

0.0

矩阵乘法 (../python/tutorials/03-matrix-multiplication.py)

02:08.338

0.0

持久化矩阵乘法 (../python/tutorials/09-persistent-matmul.py)

01:07.788

0.0

融合Softmax (../python/tutorials/02-fused-softmax.py)

00:35.218

0.0

层归一化 (../python/tutorials/05-layer-norm.py)

00:29.112

0.0

向量加法 (../python/tutorials/01-vector-add.py)

00:10.160

0.0

分组GEMM (../python/tutorials/08-grouped-gemm.py)

00:05.930

0.0

低内存Dropout (../python/tutorials/04-low-memory-dropout.py)

00:00.736

0.0

Libdevice (tl.extra.libdevice) 函数 (../python/tutorials/07-extern-functions.py)

00:00.239

0.0

块级缩放矩阵乘法 (../python/tutorials/10-block-scaled-matmul.py)

00:00.010

0.0