Skip to content

Pull requests: Dao-AILab/flash-attention

New pull request New
43 Open 162 Closed
43 Open 162 Closed
Author
Filter by author
Loading
Label
Filter by label
Loading
Use alt + click/return to exclude labels
or ⇧ + click/return for logical OR
Projects
Filter by project
Loading
Milestones
Filter by milestone
Loading
Reviews
Filter by reviews
No reviews Review required Approved review Changes requested
Assignee
Filter by who’s assigned
Sort
Sort by
Newest Oldest Most commented Least commented Recently updated Least recently updated Best match
Most reactions
👍 👎 😄 🎉 😕 ❤️ 🚀 👀

Pull requests list

FA3 kvcache + split kv + gqa parallelization
#1236 opened Sep 18, 2024 by jayhshah • Draft
3
[AMD] Triton Backend for ROCm #1
#1203 opened Sep 4, 2024 by micmelesse Loading…
3
flashattnvarlen support tree attention
#1188 opened Aug 30, 2024 by efsotr Loading…
the test_flash_attn.py it's actually in parent directory
#1167 opened Aug 21, 2024 by ArtificialZeng Loading…
Add support for qk hidden dim different from v hidden dim
#1166 opened Aug 20, 2024 by smallscientist1 Loading…
2
add softmax_d for mha_bwd
#1161 opened Aug 19, 2024 by MayDomine Loading…
Add how to import FA3 to documentation.
#1112 opened Jul 31, 2024 by AdamLouly Loading…
1
Fix: bwd may need to first allocate cuda mem for rng_state
#1077 opened Jul 20, 2024 by jundaf2 Loading…
Windows actions
#1036 opened Jul 9, 2024 by bdashore3 Loading…
1
change condition to num_heads >= num_heads_k
#1030 opened Jul 5, 2024 by Luke20000429 Loading…
1
[Draft] support qk head_dim different from vo head_dim
#980 opened Jun 6, 2024 by defei-coder Loading…
1
Fix +/-inf in LSE returned by forward
#978 opened Jun 3, 2024 by sgrigory Loading…
1
add pyproject.toml with build dependencies
#958 opened May 17, 2024 by dhellmann Loading…
5
Relative position encoding
#956 opened May 14, 2024 by b-albar Loading…
1 of 4 tasks
ALiBi for the non-flash code path
#858 opened Feb 29, 2024 by Markus28 Loading…
Add local version identifier to package metadata for pre-built wheels
#856 opened Feb 28, 2024 by yundai424 Loading…
1
2
Add support for small page sizes
#824 opened Feb 13, 2024 by skrider Loading…
24
Add C++ build support for use with LibTorch
#819 opened Feb 9, 2024 by shaltielshmid Loading…
1
meta tensor stuff
#769 opened Jan 15, 2024 by tsengalb99 Loading…
Animations for Flash Attention, Flash Attention2, and Standard Attention
#736 opened Dec 24, 2023 by LuisAVasquez Loading…
1
Jetson (aarch64) support
#724 opened Dec 14, 2023 by jasl Loading…
10
feat(attention): add Bi-Directional MLM attention model
#721 opened Dec 12, 2023 by TamirFriedman-RecoLabs • Draft
1
Update utils.py
#710 opened Dec 8, 2023 by adarshxs Loading…
2
[fix bug] Llama-2-70B crashed when prompt_len < ngroups
#708 opened Dec 7, 2023 by li2haipeng Loading…
Add flash_attn_varlen_func_with_kvcache.
#685 opened Nov 22, 2023 by garrett4wade Loading…
3
ProTip! Filter pull requests by the default branch with base:main.