Skip to content

Pull requests: Dao-AILab/flash-attention

New pull request New
54 Open 213 Closed
54 Open 213 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

feat: add support for torch2.7
#1574 opened Apr 3, 2025 by NanoCode012 • Draft
[BugFix] Ensure tensor contiguity.
#1562 opened Mar 28, 2025 by ibganev Loading…
5
Add compile support for flash_attn_with_kvcache
#1554 opened Mar 25, 2025 by ani300 Loading…
1
Implemented Flash Attention2 for Intel GPU hardware
#1528 opened Mar 6, 2025 by Wanzizhu Loading…
15
Support cuda 12.8.0 and SBSA wheels
#1507 opened Feb 25, 2025 by johnnynunez Loading…
[docs][FA3] Update build guide of FlashAttention-3
#1488 opened Feb 11, 2025 by Ethkuil Loading…
Remove ninja runtime dependency
#1484 opened Feb 9, 2025 by kevmo314 Loading…
1
2
[BugFix] Fix a wrong reference to seqlen_k variable in the fwd_splitkv kernel
#1455 opened Jan 21, 2025 by muoshuosha Loading…
1
Add missing tests/__init__.py
#1405 opened Dec 20, 2024 by BioGeek Loading…
1
Support dedicated compile[For Research]
#1384 opened Dec 12, 2024 by AllenDou • Draft
1
Fix deprecation warnings
#1382 opened Dec 12, 2024 by rongou Loading…
wrap func into torch ops to avoid torch.compile graphbreaks
#1333 opened Nov 13, 2024 by kumarkrishna Loading…
Promote wheels as alternative to pip install flash-attn
#1297 opened Oct 25, 2024 by simonw Loading…
4
fix: in newer versions of triton, tl.dot should take as input only q …
#1288 opened Oct 21, 2024 by EdouardYvinec Loading…
flashattnvarlen support tree attention
#1188 opened Aug 30, 2024 by efsotr Loading…
4
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…
5
add softmax_d for mha_bwd
#1161 opened Aug 19, 2024 by MayDomine Loading…
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 kingbri1 Loading…
7
change condition to num_heads >= num_heads_k
#1030 opened Jul 5, 2024 by xenshinu Loading…
1
[Draft] support qk head_dim different from vo head_dim
#980 opened Jun 6, 2024 by defei-coder Loading…
1
3
Fix +/-inf in LSE returned by forward
#978 opened Jun 3, 2024 by sgrigory Loading…
3
add pyproject.toml with build dependencies
#958 opened May 17, 2024 by dhellmann Loading…
16
Relative position encoding
#956 opened May 14, 2024 by b-albar Loading…
1 of 4 tasks
1
ProTip! Follow long discussions with comments:>50.