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 }}
ggml-org
/
llama.cpp
Public
Notifications
You must be signed in to change notification settings
Fork
23.4k
Star
129k
Code
Issues
887
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
Commits
Branch selector
master
User selector
All users
Datepicker
All time
Commit history
Commits on Sep 19, 2026
hexagon: enable support for TOP_K op (#29113)
Show description for 7d4b92b
aparmp-quic
authored
7d4b92b
View commit details
Copy full SHA for 7d4b92b
Browse repository at this point
server : improve startup log messages (#29125)
Show description for 1af554f
ggerganov
authored
1af554f
View commit details
Copy full SHA for 1af554f
Browse repository at this point
json-schema : accept escaped hyphen in regex patterns (#29127)
ChihebBENCHEIKH1
authored
eb1e1f4
View commit details
Copy full SHA for eb1e1f4
Browse repository at this point
metal : add MoE and SSM_CONV fusion optimizations (#28948)
Show description for 5b59b83
ggerganov
authored
5b59b83
View commit details
Copy full SHA for 5b59b83
Browse repository at this point
metal : fix FA support checks (#29122)
ggerganov
authored
60b06ab
View commit details
Copy full SHA for 60b06ab
Browse repository at this point
test-llama-archs : generate dummy test vocab (#29084)
Show description for efa28e9
ggerganov
authored
efa28e9
View commit details
Copy full SHA for efa28e9
Browse repository at this point
metal : support qwen4exp hc ops (#29000)
Show description for 59fc5a1
ggerganov
authored
59fc5a1
View commit details
Copy full SHA for 59fc5a1
Browse repository at this point
cuda : fix CUB argsort corruption caused by in-place keys (#28389)
Show description for b23701f
3 people
authored
b23701f
View commit details
Copy full SHA for b23701f
Browse repository at this point
Commits on Sep 18, 2026
opencl: add support for bin kernel `flash_attn_f32_f16_bin` (#29046)
Show description for 60081bb
dsproule
authored
60081bb
View commit details
Copy full SHA for 60081bb
Browse repository at this point
hexagon: add ROLL op support (#29105)
tboinovski1
authored
2b18470
View commit details
Copy full SHA for 2b18470
Browse repository at this point
hexagon: im2col update (#29103)
Show description for 50631b3
tboinovski1
authored
50631b3
View commit details
Copy full SHA for 50631b3
Browse repository at this point
hexagon: HMX flash-attention head_dim padding (support DK=DV=72) (#26539)
Show description for 18a04f0
tboinovski1
authored
18a04f0
View commit details
Copy full SHA for 18a04f0
Browse repository at this point
opencl: add bin kernel `kernel_gemm_noshuffle_q6_k_f32_32b_trans_ila_a8_bin` (#28678)
Show description for ec92815
shaofeiqi
authored
ec92815
View commit details
Copy full SHA for ec92815
Browse repository at this point
ggml-cpu: add F16 input to the FWHT (#27779)
Show description for 4fea119
bri-prism
authored
4fea119
View commit details
Copy full SHA for 4fea119
Browse repository at this point
ggml : check for allocation failures to prevent crashes (#28149)
Show description for 5b335f4
sanmai
authored
5b335f4
View commit details
Copy full SHA for 5b335f4
Browse repository at this point
Model-Saver: Write the SWA pattern, 15 more architectures roundtrip (#29042)
Show description for 542348a
ServeurpersoCom
authored
542348a
View commit details
Copy full SHA for 542348a
Browse repository at this point
ci: change ubuntu-latest to ubuntu-24.04 (#29079)
taronaeo
authored
d663dd3
View commit details
Copy full SHA for d663dd3
Browse repository at this point
ggml-webgpu: fix supports_op condition for GET_ROWS (#28978)
Show description for 44be98f
yomaytk
authored
44be98f
View commit details
Copy full SHA for 44be98f
Browse repository at this point
ggml : handle graph buffer reservation failure (#26070)
FaiChou
authored
911f6cd
View commit details
Copy full SHA for 911f6cd
Browse repository at this point
vulkan: add IQ3_S MMQ matmul kernels (#28822)
Show description for bbd488c
vargad
authored
bbd488c
View commit details
Copy full SHA for bbd488c
Browse repository at this point
vocab : add ufakzeka pre-tokenizer (#29033)
Show description for dc85f89
stfurkan
authored
dc85f89
View commit details
Copy full SHA for dc85f89
Browse repository at this point
cmake : fix build when GGML_CPU=OFF and GGML_CUDA=ON (#29026)
Show description for 8ed1a55
iamfobey
authored
8ed1a55
View commit details
Copy full SHA for 8ed1a55
Browse repository at this point
gguf-py: fix Q8_1 block size in GGML_QUANT_SIZES (2+2+32) (#29036)
Show description for bb11ebb
YangHong7
and
CISC
authored
bb11ebb
View commit details
Copy full SHA for bb11ebb
Browse repository at this point
ci : disable GHA cache for copilot (#29068)
CISC
authored
f03cf3e
View commit details
Copy full SHA for f03cf3e
Browse repository at this point
ci : bump android-actions/setup-android to 4.0.4 (#29065)
CISC
authored
bdcbaaf
View commit details
Copy full SHA for bdcbaaf
Browse repository at this point
vulkan: raise the hoisted row-id limit for mul_mat_id from 256 to 512 experts (#28501)
Show description for 5c53396
drluoto
authored
5c53396
View commit details
Copy full SHA for 5c53396
Browse repository at this point
Commits on Sep 17, 2026
ci : add missing evict-old-files (#29041)
CISC
authored
972d231
View commit details
Copy full SHA for 972d231
Browse repository at this point
rpc : skip ACCEL devices (#29020)
pcuenca
authored
c77ae69
View commit details
Copy full SHA for c77ae69
Browse repository at this point
model : skip gate_up_exps if TENSOR_SKIP is set (#29014)
Show description for b49650a
dfriehs
authored
b49650a
View commit details
Copy full SHA for b49650a
Browse repository at this point
model : extend Nemotron MTP support (#29018)
Show description for 7076180
frozenblade1224
authored
7076180
View commit details
Copy full SHA for 7076180
Browse repository at this point
openvino : Update OpenVINO to 2026.4;fix clangd,MSVC warnings; (#29009)
Show description for ebbb185
ravi9
and
mostafafaheem
authored
ebbb185
View commit details
Copy full SHA for ebbb185
Browse repository at this point
ui: fix removed reasoning menu in single model mode on desktop (#27985)
Show description for 4ff829e
3 people
authored
4ff829e
View commit details
Copy full SHA for 4ff829e
Browse repository at this point
vulkan: split buffers and debug code into separate files, add shared headers (#28732)
0cc4m
authored
f172be7
View commit details
Copy full SHA for f172be7
Browse repository at this point
ci : add API/ABI check to make-release workflow [no ci] (#28947)
Show description for 87f9c82
danbev
authored
87f9c82
View commit details
Copy full SHA for 87f9c82
Browse repository at this point
chat : add message delimiters to the DeepSeek V3.2/V4 parser (#29008)
Show description for 7f6f0c2
midagedev
and
CISC
authored
7f6f0c2
View commit details
Copy full SHA for 7f6f0c2
Browse repository at this point
Previous
Next
You can’t perform that action at this time.