Commit History

Author SHA1 Message Date
  Tri Dao 3b6ac2b954 Use compile time constants in local mask 1 month ago
  Tri Dao bfbaafd043 Fix bwd reading out of out LSE 1 month ago
  Tri Dao 3ed79742fb Add option to shuffle LSE and dPsum in the bwd 1 month ago
  Tri Dao 7fccac78ce Fix Mask 2 months ago
  Tri Dao a65af55f4a Move mask_fn and load_Q into separate functions 2 months ago