Commits · 4d87e4d875077ad9efd25030efa4ab0ba92c19e1 · gaoqiong / flash-attention

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
18 Jan, 2023 1 commit
- [Gen] Add OPT to generation test · f68d41ec
  Tri Dao authored Jan 17, 2023
  
  f68d41ec
15 Jan, 2023 1 commit
- [Gen] Make generation work with Tensor Parallel · 7c219154
  Tri Dao authored Jan 15, 2023
  
  7c219154
08 Jan, 2023 3 commits
- [Gen] Remove commented code · f95c2fc1
  Tri Dao authored Jan 07, 2023
  
  f95c2fc1
- [Gen] Add timing option · b4859900
  Tri Dao authored Jan 07, 2023
  
  b4859900
- [Gen] Implement top-k and top-p sampling · e02fd588
  Tri Dao authored Jan 07, 2023
  
  e02fd588
04 Jan, 2023 1 commit
- [Gen] Add option to run generation with FT attention kernel · a668890f
  Tri Dao authored Jan 03, 2023
  
  a668890f
28 Dec, 2022 2 commits
- Bump to v0.2.6 · a6ec1782
  Tri Dao authored Dec 27, 2022
  
  a6ec1782
- Implement generation for GPT · 63670fd8
  Tri Dao authored Dec 27, 2022
  
  63670fd8