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
Type
/
to 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
21.3k
Star
123k
Code
Issues
685
Pull requests
1.3k
Discussions
Actions
Projects
Wiki
Security and quality
13
Insights
Additional navigation options
Code
Issues
Pull requests
Discussions
Actions
Projects
Wiki
Security and quality
Insights
GLM 5.2 Indexer support
- #25407
#25407
Merged
ngxson
merged 13 commits into
ggml-org:master
ggml-org/llama.cpp:master
from
pcuenca:glm-dsa-indexer
pcuenca/llama.cpp:glm-dsa-indexer
Copy head branch name to clipboard
Jul 24, 2026
Conversation
Commits
13
(13)
Checks
Files changed
Merged
GLM 5.2 Indexer support
#25407
ngxson
merged 13 commits into
ggml-org:master
ggml-org/llama.cpp:master
from
pcuenca:glm-dsa-indexer
pcuenca/llama.cpp:glm-dsa-indexer
Copy head branch name to clipboard
Commits
Commits on Jul 5, 2026
Start building graph - reuse deepseek32
pcuenca
committed
58bec51
View commit details
Copy full SHA for 58bec51
Browse repository at this point
Enable kv cache and rotation for glm_dsa architecture
Show description for ab2dc71
pcuenca
committed
ab2dc71
View commit details
Copy full SHA for ab2dc71
Browse repository at this point
Reuse prev_top_k for "shared" indexer layers
pcuenca
committed
37edc79
View commit details
Copy full SHA for 37edc79
Browse repository at this point
GLM 5.2 uses LLAMA_ROPE_TYPE_NORM for the indexer.
Show description for 9d72fff
pcuenca
committed
9d72fff
View commit details
Copy full SHA for 9d72fff
Browse repository at this point
Commits on Jul 6, 2026
Default indexer types to GLM pattern
Show description for a056a18
pcuenca
committed
a056a18
View commit details
Copy full SHA for a056a18
Browse repository at this point
Commits on Jul 7, 2026
Save indexer types to gguf, restore on load
pcuenca
committed
8dedd06
View commit details
Copy full SHA for 8dedd06
Browse repository at this point
Commits on Jul 17, 2026
Merge remote-tracking branch 'origin/master' into glm-dsa-indexer
pcuenca
committed
675e120
View commit details
Copy full SHA for 675e120
Browse repository at this point
Use ggml_lightning_indexer when cparams.fused_lid
Show description for 44797a4
pcuenca
and
fairydreaming
committed
44797a4
View commit details
Copy full SHA for 44797a4
Browse repository at this point
Commits on Jul 18, 2026
GLM 5 and 5.1 use full indexers
Show description for b6f2945
pcuenca
and
fairydreaming
committed
b6f2945
View commit details
Copy full SHA for b6f2945
Browse repository at this point
Commits on Jul 24, 2026
Fix indentation
pcuenca
authored
a5fb6b7
View commit details
Copy full SHA for a5fb6b7
Browse repository at this point
Ensure array is zero-filled
pcuenca
committed
39edff0
View commit details
Copy full SHA for 39edff0
Browse repository at this point
Prefer explicit std::fill
pcuenca
committed
44b148a
View commit details
Copy full SHA for 44b148a
Browse repository at this point
Assert prev_top_k exists for shared indexer
pcuenca
committed
5286d73
View commit details
Copy full SHA for 5286d73
Browse repository at this point
You can’t perform that action at this time.