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
758
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
Add support for Laguna XS.2 & M.1
- #25165
#25165
Merged
am17an
merged 14 commits into
ggml-org:master
ggml-org/llama.cpp:master
from
joerowell:add-laguna
joerowell/llama.cpp:add-laguna
Copy head branch name to clipboard
Jul 22, 2026
Conversation
Commits
14
(14)
Checks
Files changed
Merged
Add support for Laguna XS.2 & M.1
#25165
am17an
merged 14 commits into
ggml-org:master
ggml-org/llama.cpp:master
from
joerowell:add-laguna
joerowell/llama.cpp:add-laguna
Copy head branch name to clipboard
Commits
Commits on Jul 14, 2026
convert : add Laguna (LagunaForCausalLM) support
Show description for 1fa7923
joerowell
committed
1fa7923
View commit details
Copy full SHA for 1fa7923
Browse repository at this point
llama : add Laguna model architecture
Show description for 5c9393e
joerowell
committed
5c9393e
View commit details
Copy full SHA for 5c9393e
Browse repository at this point
chat : add Laguna tool-call and reasoning parser
Show description for da04e25
joerowell
committed
da04e25
View commit details
Copy full SHA for da04e25
Browse repository at this point
conversion : address review feedback (logger + set_gguf_parameters)
Show description for b472d39
joerowell
committed
b472d39
View commit details
Copy full SHA for b472d39
Browse repository at this point
conversion : address review feedback (chat_template.jinja + dedupe set_gguf_parameters)
Show description for 3a974f0
joerowell
committed
3a974f0
View commit details
Copy full SHA for 3a974f0
Browse repository at this point
laguna : address review (dedicated vocab pre-type, converter registration, optional expert_shared_count)
joerowell
committed
3581b84
View commit details
Copy full SHA for 3581b84
Browse repository at this point
chat: laguna accepts any whitespace after tool-call name
Show description for 803964a
joerowell
committed
803964a
View commit details
Copy full SHA for 803964a
Browse repository at this point
chat: laguna accepts optional whitespace after <assistant>
Show description for 7b4abbc
joerowell
committed
7b4abbc
View commit details
Copy full SHA for 7b4abbc
Browse repository at this point
laguna: drop dedicated parser, use the autoparser
Show description for 01a86f5
joerowell
committed
01a86f5
View commit details
Copy full SHA for 01a86f5
Browse repository at this point
laguna: embed resolved chat template in the GGUF
Show description for 48eb1a6
joerowell
committed
48eb1a6
View commit details
Copy full SHA for 48eb1a6
Browse repository at this point
laguna: no chat.cpp / test-chat.cpp changes
Show description for 7d37bb7
joerowell
committed
7d37bb7
View commit details
Copy full SHA for 7d37bb7
Browse repository at this point
llama : cover laguna in test-llama-archs
Show description for f600f40
joerowell
committed
f600f40
View commit details
Copy full SHA for f600f40
Browse repository at this point
chat: tolerate Laguna tool-call whitespace in autoparser
Show description for 7dc1bfe
joerowell
committed
7dc1bfe
View commit details
Copy full SHA for 7dc1bfe
Browse repository at this point
Commits on Jul 16, 2026
chat: stop Laguna generation at literal </assistant>
Show description for 54f214a
joerowell
committed
54f214a
View commit details
Copy full SHA for 54f214a
Browse repository at this point
You can’t perform that action at this time.