yxchng
yxchng
@rentainhe which commit has the fix?
@3942368 why this occur?
For memory, do you take peak memory? The code doesn't print memory usage, does it?
@ppbangKGT have you figured out?
 The metrics given in their repo does not really show constant time and memory complexity, but increases when sequence length increases. Why PTv3 does not exhibit...
just to make sure i understand this correctly, rpe is used to get the main results in table 5 (for higher performance), but then to show efficiency in table 1,...
do you have any idea why s3dis requires rpe?
any updates?
Not CUDA memory. RAM memory using more than 500gb. 内存用很多(>500gb)，不是显存。