search

OpenNLPLab / lightning-attention

Lightning Attention-2: A Free Lunch for Handling Unlimited Sequence Lengths in Large Language Models
MIT License
184 stars 15 forks source link

question about benchmark #13

Closed Nalilik closed 6 months ago

Nalilik commented 6 months ago

bcm May I ask what's the difference between block 1 and block 3?

Doraemonzzz commented 6 months ago

This is a typo; the latter refers to the memory cost. I will update this part later.

Doraemonzzz commented 6 months ago

Fix this.