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
Accelerator
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
21.9k
Star
125k
Code
Issues
775
Pull requests
1.4k
Discussions
Actions
Projects
Wiki
Security and quality
13
Insights
Additional navigation options
Code
Issues
Pull requests
Discussions
Actions
Projects
Wiki
Security and quality
Insights
spec: support DSpark for Gemma4
- #25549
#25549
Open
wjinxu
wants to merge 10 commits into
ggml-org:master
ggml-org/llama.cpp:master
from
wjinxu:gemma4-dspark
wjinxu/llama.cpp:gemma4-dspark
Copy head branch name to clipboard
Conversation
Commits
10
(10)
Checks
Files changed
Open
spec: support DSpark for Gemma4
#25549
wjinxu
wants to merge 10 commits into
ggml-org:master
ggml-org/llama.cpp:master
from
wjinxu:gemma4-dspark
wjinxu/llama.cpp:gemma4-dspark
Copy head branch name to clipboard
Commits
Commits on Aug 18, 2026
dspark : support Gemma4 backbone drafts (WIP)
Show description for f4e67e0
wjinxu
committed
f4e67e0
View commit details
Copy full SHA for f4e67e0
Browse repository at this point
Fix GGUF conversion error
wjinxu
committed
1849dd0
View commit details
Copy full SHA for 1849dd0
Browse repository at this point
dflash: hoist the backbone FFN activation choice out of the layer loop
Show description for 3e8108f
wjinxu
and
Zaire404
committed
3e8108f
View commit details
Copy full SHA for 3e8108f
Browse repository at this point
dspark: update the docs for the p-min fold and Gemma4 backbone, drop a stale TODO
Show description for 9ba0141
wjinxu
and
Zaire404
committed
9ba0141
View commit details
Copy full SHA for 9ba0141
Browse repository at this point
dspark: split the Gemma4 draft graph into a separate class
Show description for 75cf5ef
wjinxu
committed
75cf5ef
View commit details
Copy full SHA for 75cf5ef
Browse repository at this point
convert: align Gemma4DSparkModel set_vocab with the DSV4 converter
Show description for ab11833
wjinxu
committed
ab11833
View commit details
Copy full SHA for ab11833
Browse repository at this point
dspark: shorten the Gemma4 graph comment, generalize the backbone doc
Show description for 5e56e84
wjinxu
committed
5e56e84
View commit details
Copy full SHA for 5e56e84
Browse repository at this point
dspark: load the Gemma4 backbone tensors in a dedicated early-exit branch
Show description for 7817cab
wjinxu
committed
7817cab
View commit details
Copy full SHA for 7817cab
Browse repository at this point
convert: slim down the Gemma4 DSpark converter, drop the FFN_PRE_NORM alias
Show description for c5171c9
wjinxu
committed
c5171c9
View commit details
Copy full SHA for c5171c9
Browse repository at this point
dspark: fold the Gemma4 draft graph into the shared DFlash decoder
Show description for 3fdaf0b
wjinxu
and
desovo7
committed
3fdaf0b
View commit details
Copy full SHA for 3fdaf0b
Browse repository at this point
You can’t perform that action at this time.