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 }}
ggml-org
/
llama.cpp
Public
Notifications
You must be signed in to change notification settings
Fork
24.1k
Star
130k
Code
Issues
867
Pull requests
1.7k
Discussions
Actions
Projects
Wiki
Security and quality
13
Insights
Additional navigation options
Code
Issues
Pull requests
Discussions
Actions
Projects
Wiki
Security and quality
Insights
vulkan: support sparse Flash Attention
- #28105
#28105
Merged
ggerganov
merged 7 commits into
master
ggml-org/llama.cpp:master
from
0cc4m/vulkan-fa-sparse
ggml-org/llama.cpp:0cc4m/vulkan-fa-sparse
Copy head branch name to clipboard
Sep 15, 2026
Conversation
Commits
7
(7)
Checks
Files changed
Merged
vulkan: support sparse Flash Attention
#28105
ggerganov
merged 7 commits into
master
ggml-org/llama.cpp:master
from
0cc4m/vulkan-fa-sparse
ggml-org/llama.cpp:0cc4m/vulkan-fa-sparse
Copy head branch name to clipboard
Commits
Commits on Sep 11, 2026
vulkan: add sparse Flash Attention support for DSV4/GLM
0cc4m
committed
f4d1e06
View commit details
Copy full SHA for f4d1e06
Browse repository at this point
tune implementation
0cc4m
committed
9d624c7
View commit details
Copy full SHA for 9d624c7
Browse repository at this point
add tests
0cc4m
committed
5cfc32c
View commit details
Copy full SHA for 5cfc32c
Browse repository at this point
Commits on Sep 14, 2026
avoid nondeterministic atomicAdd
0cc4m
committed
4191ad1
View commit details
Copy full SHA for 4191ad1
Browse repository at this point
add cm2 decode vector support
0cc4m
committed
8d9b181
View commit details
Copy full SHA for 8d9b181
Browse repository at this point
simplify logic and make variable names more consistent
0cc4m
committed
de18aa9
View commit details
Copy full SHA for de18aa9
Browse repository at this point
add cm2 f16vec4 binding for decode vector
0cc4m
committed
201031a
View commit details
Copy full SHA for 201031a
Browse repository at this point
You can’t perform that action at this time.
