Skip to content
Navigation Menu
Sign in
Appearance settings
Platform
AI CODE CREATION
GitHub Copilot
Write better code with AI
GitHub Copilot app
Direct agents from issue to merge
MCP Registry
Integrate external tools
DEVELOPER WORKFLOWS
Actions
Automate any workflow
Codespaces
Instant dev environments
Issues
Plan and track work
Code Review
Manage code changes
Code Quality
Enforce quality at merge
APPLICATION SECURITY
GitHub Advanced Security
Find and fix vulnerabilities
Code security
Secure your code as you build
Secret protection
Stop leaks before they start
EXPLORE
Why GitHub
Documentation
Blog
Changelog
Marketplace
View all features
Solutions
BY COMPANY SIZE
Enterprises
Small and medium teams
Startups
Nonprofits
BY USE CASE
App Modernization
DevSecOps
DevOps
CI/CD
View all use cases
BY INDUSTRY
Healthcare
Financial services
Manufacturing
Government
View all industries
View all solutions
Resources
EXPLORE BY TOPIC
AI
Software Development
DevOps
Security
View all topics
EXPLORE BY TYPE
Customer stories
Events & webinars
Ebooks & reports
Business insights
GitHub Skills
SUPPORT & SERVICES
Documentation
Customer support
Community forum
Trust center
Partners
View all resources
Open Source
COMMUNITY
GitHub Sponsors
Fund open source developers
PROGRAMS
Security Lab
Maintainer Community
GitHub Stars
Archive Program
REPOSITORIES
Topics
Trending
Collections
Enterprise
ENTERPRISE SOLUTIONS
Enterprise platform
AI-powered developer platform
AVAILABLE ADD-ONS
GitHub Advanced Security
Enterprise-grade security features
Copilot for Business
Enterprise-grade AI features
Premium Support
Enterprise-grade 24/7 support
Pricing
Search
/
Sign in
Sign up
Appearance settings
You signed in with another tab or window.
Reload
to refresh your session.
You signed out in another tab or window.
Reload
to refresh your session.
You switched accounts on another tab or window.
Reload
to refresh your session.
Dismiss alert
{{ message }}
fla-org
flash-linear-attention
Repository navigation
Code
Issues
46
(46)
Pull requests
77
(77)
Discussions
Actions
Projects
Wiki
Security and quality
Insights
More
items
All pull requests
Labels
23
(23)
Milestones
3
(3)
New pull request
Search pull requests
is
:
pr
state
:
open
is:pr state:open
Clear filter
Search
Pull requests
Open
77
(77)
Closed
871
(871)
Author
Label
Projects
Milestones
Reviews
Assignee
Sort by
Newest
descending
Sort…
Sort by Newest descending
More items
Comfortable display density
Compact display density
[Ops] Add Triadic Gated DeltaNet reference implementation
#1371
·
ischencheng
opened
Oct 11, 2026
·
4 of 6 tasks
·
·
[Model] Add Gated Slot Attention 2 (GSA2) with the Oja2 operator
#1365
·
ReyJerry
opened
Oct 10, 2026
Contributor
·
5 of 6 tasks
·
·
6
[Perf] Reuse cumsum and dqkwg compilations across batch sizes
#1359
·
garyriver
opened
Oct 10, 2026
·
3 of 6 tasks
·
·
1
[GKA] Add Gated KalmaNet op, layer, and model
#1352
·
elvisnunez7
opened
Oct 9, 2026
·
5 of 6 tasks
·
·
[Ops] Add Triton-Ascend support for momentum delta rule
ascend-npu
#1343
·
TecJesh
opened
Oct 8, 2026
Contributor
·
5 of 6 tasks
·
·
4
[Ops] Add Triton-Ascend support for preconditioned GDN
ascend-npu
#1342
·
sunyi0505
opened
Oct 8, 2026
Contributor
·
5 of 6 tasks
·
·
3
[Ops] Incorporate mLSTM kernels and layers into FLA
#1341
·
hoedt
opened
Oct 8, 2026
Contributor
·
5 of 6 tasks
·
·
[Fix] Version-gate Blackwell eight-warp chunk configs
#1336
·
arcusbuilds
opened
Oct 7, 2026
·
·
[Refactor] Unify residual implementations with an extensible interface
enhancement
#1331
·
feiyunzhang
opened
Oct 6, 2026
Contributor
·
4 of 5 tasks
·
·
1
[Ops] Add Gluon attention up to head dimension 512
performance
#1324
·
yzhangcs
opened
Oct 3, 2026
Member
·
4 of 6 tasks
·
·
5
[Perf] Eliminate log-linear level transfers and parallelize recurrent work
performance
#1323
·
ZenAlexa
opened
Oct 3, 2026
Contributor
·
4 of 6 tasks
·
·
1
[Fix] Match HGRN lower bounds to expanded recurrent width
bug
#1318
·
taking-lying-flat
opened
Sep 30, 2026
Contributor
·
4 of 5 tasks
·
·
[Perf] Replace Ascend GDN bwd_dhu with a oneslab kernel, hoist fwd_h chunk loads
ascend-npu
performance
#1317
·
qianjinqiu
opened
Sep 30, 2026
Contributor
·
5 of 6 tasks
·
·
9
[Model] Add the Diagonal Kalman Delta Network (DiagKDN)
enhancement
#1316
·
ngocbh
opened
Sep 29, 2026
·
5 of 6 tasks
·
·
1
[Fix] Preserve explicit packed boundaries in preconditioned layers
bug
#1314
·
syc632
opened
Sep 29, 2026
·
4 of 5 tasks
·
·
[Fix] Honor indexed recurrent KDA state storage
bug
#1313
·
ZenAlexa
opened
Sep 29, 2026
Contributor
·
4 of 6 tasks
·
·
1
[Fix] Accept precomputed GDP chunk indices for CUDA graph capture
bug
#1312
·
wujingyue
opened
Sep 29, 2026
·
3 of 5 tasks
·
·
[Fix] Validate head dim divisibility in layers that truncate it
bug
#1311
·
aniruddhaadak80
opened
Sep 29, 2026
Contributor
·
4 of 5 tasks
·
·
[Model] Add the Isotropic Kalman Delta Network (IsoKDN)
enhancement
#1309
·
ngocbh
opened
Sep 28, 2026
·
4 of 5 tasks
·
·
1
[Perf] Tune recurrent KDA value tiling
performance
#1308
·
ZenAlexa
opened
Sep 28, 2026
Contributor
·
4 of 6 tasks
·
·
1
[Fix] Count new tokens, not key dim, in the MoM cache offset
bug
#1306
·
aniruddhaadak80
opened
Sep 28, 2026
Contributor
·
4 of 5 tasks
·
·
[Fix] Honor the attention mask in the fused Mamba training path
bug
#1304
·
aniruddhaadak80
opened
Sep 28, 2026
Contributor
·
4 of 5 tasks
·
·
[Fix] Forward the configured epsilon in the bit-linear norm
bug
#1303
·
aniruddhaadak80
opened
Sep 28, 2026
Contributor
·
4 of 5 tasks
·
·
[Perf] Avoid zero-filling dense recurrent KDA outputs
performance
#1301
·
ZenAlexa
opened
Sep 28, 2026
Contributor
·
4 of 6 tasks
·
·
1
[Fix] Preserve sliding-window context for cached chunks
bug
#1300
·
cyanseek
opened
Sep 28, 2026
Contributor
·
4 of 5 tasks
·
·
Previous
1
2
3
4
Next
You can’t perform that action at this time.