Commits · ff34123bd426bcc3ca0d1a11b6173652fb84d033 · gaoqiong / flash-attention

16 Jan, 2023 1 commit
- Reorder LN in Block, support OPT · ff34123b
  Tri Dao authored Jan 15, 2023
  
  ff34123b
07 Jan, 2023 1 commit
- [TP] Implement TensorParallel without sequence parallel · 93383bd5
  Tri Dao authored Jan 07, 2023
  
  93383bd5
02 Jan, 2023 1 commit
- [TP] Put parallel embeddings in separate modules · 4cab4de5
  Tri Dao authored Jan 02, 2023
  
  4cab4de5
25 Dec, 2022 1 commit
- Implement Tensor Parallel for GPT2Embeddings · 78225c53
  Tri Dao authored Dec 25, 2022
  
  78225c53
19 Dec, 2022 1 commit
- Implement BERT · 5fb6df0e
  Tri Dao authored Dec 18, 2022
  
  5fb6df0e
14 Nov, 2022 1 commit
- Add MLP, MHA, Block, Embedding modules · d4b320b3
  Tri Dao authored Nov 13, 2022
  
  d4b320b3