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
22.1k
Star
126k
Code
Issues
822
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
Commits
Branch selector
master
User selector
All users
Datepicker
All time
Commit history
Commits on Aug 25, 2026
sync : ggml
ggerganov
committed
81191af
View commit details
Copy full SHA for 81191af
Browse repository at this point
ggml : bump version to 0.22.0 (ggml/1607)
Show description for 9388236
ggerganov
committed
9388236
View commit details
Copy full SHA for 9388236
Browse repository at this point
grammar : parse \- in char classes as literal hyphen (#27591)
Show description for eb25b72
NIXKnight
authored
eb25b72
View commit details
Copy full SHA for eb25b72
Browse repository at this point
sycl : mark tq2_0 as not supported (#27660)
arthw
authored
814d84b
View commit details
Copy full SHA for 814d84b
Browse repository at this point
webgpu : fix handling of infinity values during ARGSORT and TOP_K (#27538)
Show description for 5ea87dd
fairydreaming
and
sszymczy
authored
5ea87dd
View commit details
Copy full SHA for 5ea87dd
Browse repository at this point
Commits on Aug 24, 2026
metal : per-device tuned (Q, NE) for flash-attn vec (#26570)
Show description for f280b26
forforever73
and
ggerganov
authored
f280b26
View commit details
Copy full SHA for f280b26
Browse repository at this point
metal: per-op source split + parallel compile (#26561)
Show description for b615f5b
3 people
authored
b615f5b
View commit details
Copy full SHA for b615f5b
Browse repository at this point
misc : read repetition_penalty from generation_config.json (#27659)
Show description for b3c3b96
tdakhran
authored
b3c3b96
View commit details
Copy full SHA for b3c3b96
Browse repository at this point
tests : disable DOTS3NOTE arch test for WebGPU (#27654)
Show description for 7584430
fairydreaming
and
sszymczy
authored
7584430
View commit details
Copy full SHA for 7584430
Browse repository at this point
convert: fix GLM regression in index_tensors (#27655)
jacekpoplawski
authored
71cc86f
View commit details
Copy full SHA for 71cc86f
Browse repository at this point
ggml : shorten virtual device naming in CUDA and Metal (#27608)
Show description for a14dba6
ggerganov
authored
a14dba6
View commit details
Copy full SHA for a14dba6
Browse repository at this point
webgpu : reorder includes since V that appears in common_decls.tmpl may be defined as K in flash_attn_decls.tmpl if KV_OVERLAP (#27545)
Show description for c1c766d
fairydreaming
and
sszymczy
authored
c1c766d
View commit details
Copy full SHA for c1c766d
Browse repository at this point
mtmd: video: fix moov atom at the end of file (#27596)
Show description for 160c6b0
ngxson
and
rkfg
authored
160c6b0
View commit details
Copy full SHA for 160c6b0
Browse repository at this point
ci : apply ccache-clear with older/min/dry-run to all ccache jobs (#27602)
Show description for 985b149
ggerganov
authored
985b149
View commit details
Copy full SHA for 985b149
Browse repository at this point
ggml : fix ggml_clamp (#27644)
Show description for 6036c63
ggerganov
authored
6036c63
View commit details
Copy full SHA for 6036c63
Browse repository at this point
mamba2 : Flatten in/out projections to dispatch GEMM instead of GEMV (#27513)
Show description for a130532
pskrunner14
authored
a130532
View commit details
Copy full SHA for a130532
Browse repository at this point
Deepseek 4: `-sm tensor` (#26490)
Show description for bf0a29c
am17an
authored
bf0a29c
View commit details
Copy full SHA for bf0a29c
Browse repository at this point
Commits on Aug 23, 2026
model : support MTP in GLM-4.5-Air (#26534)
jacekpoplawski
authored
c060ca9
View commit details
Copy full SHA for c060ca9
Browse repository at this point
readme : update links (#27617)
Show description for ccc8fd2
ggerganov
authored
ccc8fd2
View commit details
Copy full SHA for ccc8fd2
Browse repository at this point
fix: Change chat tabs nav shortcuts (#27609)
allozaur
authored
d05f895
View commit details
Copy full SHA for d05f895
Browse repository at this point
test : fix multi-GPU server tests (#27614)
Show description for 8d9af25
ggerganov
authored
8d9af25
View commit details
Copy full SHA for 8d9af25
Browse repository at this point
test: move tools/parser to tests (#27548)
ngxson
authored
4a08fa2
View commit details
Copy full SHA for 4a08fa2
Browse repository at this point
mtmd: use pillow-accurate algo, correct resize_algo for all models (#27594)
Show description for 56db501
ngxson
authored
56db501
View commit details
Copy full SHA for 56db501
Browse repository at this point
ci : add test-llama-archs tensor split for Metal (#27598)
Show description for 95b8e33
ggerganov
authored
95b8e33
View commit details
Copy full SHA for 95b8e33
Browse repository at this point
contrib : recommend waiting for CI before merging (#27603)
nikwen
authored
a278dce
View commit details
Copy full SHA for a278dce
Browse repository at this point
server : add LLAMA_SERVER_SLOTS_N_DIFF (#27600)
ggerganov
authored
e8eed45
View commit details
Copy full SHA for e8eed45
Browse repository at this point
common : skip device_info loop if it's not going to be printed (#26692)
Show description for ba8e0ed
wolfpld
authored
ba8e0ed
View commit details
Copy full SHA for ba8e0ed
Browse repository at this point
DeepseekV4: fix rollback with multi-seq (#26756)
Show description for b0539c4
am17an
and
ggerganov
authored
b0539c4
View commit details
Copy full SHA for b0539c4
Browse repository at this point
[Tensor parallel] Fix meta tensor split state propagation (#27574)
Show description for d337192
gaugarg-nv
authored
d337192
View commit details
Copy full SHA for d337192
Browse repository at this point
ui: Chat Conversation Tabbed navigation (#27263)
Show description for 8144f31
allozaur
and
ServeurpersoCom
authored
8144f31
View commit details
Copy full SHA for 8144f31
Browse repository at this point
vendor : update subprocess.h (#27409)
cabelo
authored
6657ded
View commit details
Copy full SHA for 6657ded
Browse repository at this point
cuda : add POOL_1D support (#27573)
Show description for 29ea941
amankarki151
authored
29ea941
View commit details
Copy full SHA for 29ea941
Browse repository at this point
Commits on Aug 22, 2026
common: json.h: fix clang lto (#27575)
ngxson
authored
70adb1b
View commit details
Copy full SHA for 70adb1b
Browse repository at this point
vulkan : added the PAD_REFLECT_1D operation (#26586)
Show description for 3f545be
safiullah3915
and
jeffbolznv
authored
3f545be
View commit details
Copy full SHA for 3f545be
Browse repository at this point
mtmd: use ggml_rope_set_offset (#27521)
Show description for b21e4de
ngxson
authored
b21e4de
View commit details
Copy full SHA for b21e4de
Browse repository at this point
Previous
Next
You can’t perform that action at this time.
