- 21 Oct, 2022 1 commit
-
-
Tri Dao authored
They don't have to have the same block size, number of threads, etc.
-
- 14 Oct, 2022 2 commits
- 06 Oct, 2022 1 commit
-
-
Antoine Adam authored
According to the `setup.py` file, only dependencies are torch and einops. But the `bert_padding.py` file requires `numpy` only to multiply the elements of a `torch.Size` object. This change aims at allowing the use of FlashAttention without numpy.
-
- 11 Sep, 2022 1 commit
-
-
Tri Dao authored
-
- 06 Sep, 2022 1 commit
-
-
eric-tc-wong authored
Recasting query and key after rotary_emb()
-
- 09 Aug, 2022 1 commit
-
-
Tri Dao authored
-
- 05 Aug, 2022 2 commits
- 04 Jul, 2022 2 commits
- 03 Jul, 2022 1 commit
-
-
Gustaf authored
-
- 02 Jun, 2022 1 commit
-
-
Tri Dao authored
-
