Commits · 96d10f654527cc82c81022e16f77a8d9564f7eba · gaoqiong / flash-attention

19 Apr, 2023 1 commit
- Implement LLaMa · 96d10f65
  Tri Dao authored Apr 18, 2023
  
  96d10f65
22 Mar, 2023 1 commit
- Implement GPT-J · 4d87e4d8
  Tri Dao authored Mar 22, 2023
  
  4d87e4d8
23 Jan, 2023 1 commit
- [OPT] Load fp16 weights on CPU before moving to GPU · 78b7a1dc
  Tri Dao authored Jan 22, 2023
  
  78b7a1dc
16 Jan, 2023 1 commit
- Reorder LN in Block, support OPT · ff34123b
  Tri Dao authored Jan 15, 2023
  
  ff34123b