Skip to content

Releases: lucidrains/native-sparse-attention-pytorch

0.0.65

28 Feb 18:09
Compare
Choose a tag to compare
remove the get_at from inference

0.0.64

28 Feb 17:51
Compare
Choose a tag to compare
make it right for now, optimizer later

0.0.63

28 Feb 17:41
Compare
Choose a tag to compare
complete the overall idea for inference, polish up the edge cases on …

0.0.62

28 Feb 16:15
Compare
Choose a tag to compare
fix

0.0.61

28 Feb 16:10
Compare
Choose a tag to compare
start with compressed and sliding window for inference

0.0.60

28 Feb 13:50
Compare
Choose a tag to compare
precautionary

0.0.59

28 Feb 13:35
Compare
Choose a tag to compare
allow for block causal to be turned off for the triton kernel, preppi…

0.0.58

28 Feb 00:12
Compare
Choose a tag to compare
move query head group dimension to the right by one in forward triton…

0.0.57

27 Feb 17:59
Compare
Choose a tag to compare
move grouped query head dimension to the right by one and cleanup bac…

0.0.56

27 Feb 16:31
Compare
Choose a tag to compare
prepare for knocking out inference logic over the weekend, last commi…