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
See 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 }}
incoai
splash
Repository navigation
Code
Issues
45
(45)
Pull requests
53
(53)
Discussions
Actions
Security and quality
Insights
More
items
All pull requests
Labels
9
(9)
Milestones
0
(0)
New pull request
Search pull requests
is
:
pr
state
:
open
is:pr state:open
Clear filter
Search
Pull requests
Open
53
(53)
Closed
335
(335)
Author
Label
Projects
Milestones
Reviews
Assignee
Sort by
Newest
descending
Sort…
Sort by Newest descending
More items
Comfortable display density
Compact display density
Use smaller SIMD-group rows for short affine FFN prefills on M5 Pro
#585
·
linson007
opened
Oct 24, 2026
Contributor
·
·
1
Use M16 for measured one-lane AF4G64 decode on M5 Pro
#584
·
linson007
opened
Oct 24, 2026
Contributor
·
·
Report complete decode cycles and publish Qwen M5 Pro evidence
#583
·
linson007
opened
Oct 24, 2026
Contributor
·
·
1
Keep a waiting lane's pooled buffers when KV reclaims idle state
#579
·
Litee
opened
Oct 24, 2026
·
·
Stage GGUF MoE experts on Apple9 GPUs of 10 cores or fewer
#578
·
jianc99
opened
Oct 24, 2026
Collaborator
·
·
Check the host's reserve before Ready without the warmups' idle lanes
#577
·
jianc99
opened
Oct 24, 2026
Collaborator
·
·
1
1
Serve Flint (RecursiveSI/flint) from its GGUFs
#576
·
jianc99
opened
Oct 24, 2026
Collaborator
·
·
1
Give each family its own chat format, and derive Flint's configuration from its GGUF
#575
·
jianc99
opened
Oct 24, 2026
Collaborator
·
·
Run targets without GDN layers, and trim sliding windows' K/V from cached pages
#574
·
jianc99
opened
Oct 24, 2026
Collaborator
·
·
Compile the attention, MoE and stop-token variants Flint runs
#573
·
jianc99
opened
Oct 24, 2026
Collaborator
·
·
Decode zero-point formats with fewer chains on Apple9's register tile
#569
·
ghisguth
opened
Oct 23, 2026
·
·
Add Qwen3.5-4B target and DFlash2 draft support
#559
·
Qiqi723
opened
Oct 23, 2026
·
·
Document the backend-benchmark figures for a 128 GB M5 Max
#557
·
guillermolc
opened
Oct 22, 2026
·
·
Add matched-prefix DFlash state restore probes and native evidence
#556
·
linson007
opened
Oct 22, 2026
Contributor
·
·
1
Add matched-context DFlash proposal policy overlap reference
#555
·
linson007
opened
Oct 22, 2026
Contributor
·
·
1
Add selective recall training and reached-prefix coverage metrics
#554
·
linson007
opened
Oct 22, 2026
Contributor
·
·
1
Add training-only pair-context and nonlinear selector prototypes
#553
·
linson007
opened
Oct 22, 2026
Contributor
·
·
1
Add experimental prefix-survival loss and position weighting
#552
·
linson007
opened
Oct 22, 2026
Contributor
·
·
1
Add experimental loader-matched AF4G64 projection training
#551
·
linson007
opened
Oct 22, 2026
Contributor
·
·
1
Add DFlash acceptance capture and offline selector analysis
#550
·
linson007
opened
Oct 22, 2026
Contributor
·
·
1
1
Add ability to use custom templates
#549
·
Ptico
opened
Oct 22, 2026
·
·
2
Add experimental Apple Silicon MPS draft training
#537
·
linson007
opened
Oct 21, 2026
Contributor
·
·
1
Serve a model without a draft with
--draft-model none
#534
·
Flo5k5
opened
Oct 21, 2026
·
·
1
1
Steer Qwen3.8-Flash-Next, Qwen3.8-27B and Qwen3.6-35B-A3B with a control vector (
--control-vector
)
#532
·
Flo5k5
opened
Oct 21, 2026
·
·
1
Encode chat-template tags quoted in message text as plain text
#530
·
Flo5k5
opened
Oct 21, 2026
·
·
Previous
1
2
3
Next
You can’t perform that action at this time.