Skip to content

Pull requests: vllm-project/flash-attention

New pull request New
7 Open 28 Closed
7 Open 28 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

Avoid clobbering query in ref_paged_attn
#35 opened Jan 6, 2025 by tlrmchlsmth Loading…
Add sparse attention with vertical and slash
#33 opened Dec 19, 2024 by minminsun Loading…
33
support KV-Compress paged KV cache
#27 opened Nov 27, 2024 by IsaacRe Loading…
4
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! Exclude everything labeled bug with -label:bug.