Replies: 1 comment
-
InternLM/InternEvo#33 |
Beta Was this translation helpful? Give feedback.
0 replies
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
-
InternLM/InternEvo#33 |
Beta Was this translation helpful? Give feedback.
-
From the Image above, we can see that the item() operation over indexes.max() comsumes too much time. Can we instead passing the seq length to remove this operation?
如图, 可以看到item操作在每一层计算时都被调用执行。是否可以考虑传入seqlength跳过这部分的取值?
Beta Was this translation helpful? Give feedback.
All reactions