Home Explore Help
Register Sign In
david
/
flash-attention
mirror of https://github.com/Dao-AILab/flash-attention
1
0
Fork 0
Files Issues 0 Wiki
Branch: varlen
Branches Tags

Commit History

Author SHA1 Message Date
  Tri Dao 393882bc08 [LayerNorm] Implement LN with parallel residual, support dim 8k 1 year ago
  Tri Dao 6738d9477d [LayerNorm] Implement RMS Norm 1 year ago
  Tri Dao ae137ed17a [LayerNorm] Fuse LayerScale 2 years ago
  Tri Dao 8c6609ae1a [LayerNorm] Support all dimensions up to 6k (if divisible by 8) 2 years ago
  Tri Dao fa6d1ce44f Add fused_dense and dropout_add_layernorm CUDA extensions 2 years ago