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 }}
Uh oh!
There was an error while loading.
Please reload this page
.
ggml-org
/
llama.cpp
Public
Notifications
You must be signed in to change notification settings
Fork
22.9k
Star
128k
Code
Issues
898
Pull requests
1.6k
Discussions
Actions
Projects
Wiki
Security and quality
13
Insights
Additional navigation options
Code
Issues
Pull requests
Discussions
Actions
Projects
Wiki
Security and quality
Insights
CUDA + ggml: add sparse-fa for DSV4/GLM
- #27970
#27970
Merged
ggerganov
merged 8 commits into
ggml-org:master
ggml-org/llama.cpp:master
from
am17an:sparse-fa
am17an/llama.cpp:sparse-fa
Copy head branch name to clipboard
Sep 2, 2026
Conversation
Commits
8
(8)
Checks
Files changed
Merged
CUDA + ggml: add sparse-fa for DSV4/GLM
#27970
ggerganov
merged 8 commits into
ggml-org:master
ggml-org/llama.cpp:master
from
am17an:sparse-fa
am17an/llama.cpp:sparse-fa
Copy head branch name to clipboard
Commits
Commits on Sep 1, 2026
CUDA + ggml: add sparse flash attention
am17an
committed
5577abb
View commit details
Copy full SHA for 5577abb
Browse repository at this point
fix PDL issues
am17an
committed
33a4035
View commit details
Copy full SHA for 33a4035
Browse repository at this point
remove sparse hint
am17an
committed
92b5b18
View commit details
Copy full SHA for 92b5b18
Browse repository at this point
cont: fix PDL placement
am17an
committed
be029fd
View commit details
Copy full SHA for be029fd
Browse repository at this point
add comments to endif, add unroll, fix formatting
am17an
committed
e6b567e
View commit details
Copy full SHA for e6b567e
Browse repository at this point
address rest of the review comments
am17an
committed
999a81d
View commit details
Copy full SHA for 999a81d
Browse repository at this point
perf improvments suggested by Johannes
am17an
committed
fb29470
View commit details
Copy full SHA for fb29470
Browse repository at this point
Commits on Sep 2, 2026
s/set_sparse/set_n_kv_max/g
am17an
committed
9ff4921
View commit details
Copy full SHA for 9ff4921
Browse repository at this point
You can’t perform that action at this time.
