Skip to content

Commit 05d0764

Browse files
Xia-WeiwenXia-Weiwen
authored
WOQ: Optimize quantization of activation (#2584)
* WOQ: Optimize quantization per-tensor/per-block of activation for lowp-mode=INT8 * Refine threshold of activation size to parallelize quantization
1 parent 444d17e commit 05d0764

File tree

1 file changed

+534
-136
lines changed

1 file changed

+534
-136
lines changed

0 commit comments

Comments
 (0)