Skip to content

Pull requests: vllm-project/flash-attention

New pull request New
15 Open 85 Closed
15 Open 85 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
Assigned to nobody Loading
Sort
Sort by
Newest Oldest Most commented Least commented Recently updated Least recently updated Best match
Most reactions
👍 👎 😄 🎉 😕 ❤️ 🚀 👀

Pull requests list

Add DCP parameters
#92 opened Sep 16, 2025 by MatthewBonanni • Draft
2
Vllm_flash_attn_with_attention_weights
#88 opened Sep 11, 2025 by SiriusPaul Loading…
FA3 variable length attention sort/swizzle
#82 opened Aug 22, 2025 by jayhshah Loading…
4
feat: implement tree attention mask support for FlashAttention-2
#81 opened Aug 15, 2025 by foolusion Loading…
20
WIP stream k scheduling
#67 opened Apr 29, 2025 by LucasWilkinson • Draft
sync
#65 opened Apr 23, 2025 by AlpinDale Loading…
Removed the assertion imposed on cu_seqlens_k and seqused_k
#59 opened Mar 29, 2025 by chenyang78 Loading…
19
fix: add "typename" prior to dependent type name
#54 opened Feb 28, 2025 by zhiweij1 Loading…
1
AMD ROCm Build
#41 opened Jan 29, 2025 by ProExpertProg • Draft
Add back flash_attn_func api (and support FA3) [Don't Merge Yet]
#40 opened Jan 26, 2025 by LucasWilkinson Loading…
support KV-Compress paged KV cache
#27 opened Nov 27, 2024 by IsaacRe Loading…
5
Add CUDA 8.7 arch for Jetson Orin
#26 opened Nov 27, 2024 by conroy-cheers Loading…
Update torch to 2.5.1
#25 opened Nov 7, 2024 by ayakzob Loading…
Don't disable uneven k to support more headdims
#21 opened Sep 27, 2024 by njhill Loading…
6
Update .gitignore to ignore *env/ directories
#16 opened Aug 8, 2024 by wasertech Loading…
ProTip! Find all pull requests that aren't related to any open issues with -linked:issue.