Skip to content

Pull requests: fla-org/flash-linear-attention

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
Assignee
Filter by who’s assigned
Assigned to nobody Loading
Sort

Pull requests list

[Cache] FLA autotune cache
#798 opened Mar 29, 2026 by sBobHuang Loading…
[GDN] Tricked kernels: ungated KKT + fused inference via similarity transform
#797 opened Mar 28, 2026 by hypnopump Contributor Loading…
5 tasks
[Layernorm] Fix autotuner crash and OOB writes in layer_norm_bwd on high-SM GPUs
#796 opened Mar 28, 2026 by mpurland Contributor Loading…
5 tasks done
Add LinOSS model(ICLR 2025 oral)
#749 opened Feb 17, 2026 by Phoenix8215 Loading…
[Cache] Cache Triton Autotune
#705 opened Dec 30, 2025 by zhiyuan1i Collaborator Draft
Add fused short convolution kernel with L2 norm
#661 opened Nov 24, 2025 by sustcsonglin Collaborator Loading…
[kda] add recursive block intra implementation
#656 opened Nov 22, 2025 by sustcsonglin Collaborator Loading…
Update README.md of ops delta_rule
#595 opened Sep 17, 2025 by SeepingFragranceLock Contributor Loading…
Cached inference for NSA
#574 opened Aug 22, 2025 by mutiann Contributor Loading…
Modify output shape in nsa for decoding
#565 opened Aug 14, 2025 by Espere-1119-Song Loading…
Updated the Technical Note for WY of DPLR
#562 opened Aug 12, 2025 by phnazari Loading…
Delta Product Rule Backwards Kernel
#526 opened Jul 14, 2025 by phi-jkim Loading…
ProTip! Adding no:label will show everything without a label.