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
.
actual-computer
/
llama.cpp
Public
forked from
ggml-org/llama.cpp
Notifications
You must be signed in to change notification settings
Fork
0
Star
1
Code
Pull requests
0
Actions
Projects
Security and quality
0
Insights
Additional navigation options
Code
Pull requests
Actions
Projects
Security and quality
Insights
Commits
Branch selector
master
User selector
All users
All time
Commit history
Commits on Aug 4, 2025
vulkan: fix build when using glslang that does not support coopmat2 (#15062)
jeffbolznv
authored
5aa1105
View commit details
Copy full SHA for 5aa1105
Browse repository at this point
Commits on Aug 3, 2025
imatrix : use GGUF by default (#14842)
Show description for d31192b
compilade
authored
d31192b
View commit details
Copy full SHA for d31192b
Browse repository at this point
imatrix : fix 3d activation handling for hybrid and recurrent models (#14994)
Show description for 0a2f549
compilade
authored
0a2f549
View commit details
Copy full SHA for 0a2f549
Browse repository at this point
memory : handle kv_unified for hybrid models (#15050)
compilade
authored
11a3811
View commit details
Copy full SHA for 11a3811
Browse repository at this point
vocab : JetBrains Mellum pre-tokenizer (#15045)
csabakecskemeti
authored
97366dc
View commit details
Copy full SHA for 97366dc
Browse repository at this point
model : add text-only support for Kimi-VL (and find special tokens in text_config) (#15051)
Show description for 83bc2f2
gabriellarson
authored
83bc2f2
View commit details
Copy full SHA for 83bc2f2
Browse repository at this point
vulkan: Use coopmat2 for conv2d (#14982)
jeffbolznv
authored
6c7a441
View commit details
Copy full SHA for 6c7a441
Browse repository at this point
Commits on Aug 2, 2025
opencl: fix adreno compiler detection logic (#15029)
lhez
authored
5c0eb5e
View commit details
Copy full SHA for 5c0eb5e
Browse repository at this point
CUDA: use mma FA kernel for gqa > 4 on RTX 4000 (#15035)
JohannesGaessler
authored
03d4698
View commit details
Copy full SHA for 03d4698
Browse repository at this point
cuda: make im2col a little faster (#15025)
leejet
authored
3303c19
View commit details
Copy full SHA for 3303c19
Browse repository at this point
kv-cache : skip alignment of n_stream in kv-cache log msg [no ci] (#15040)
Show description for 4fdea54
danbev
authored
4fdea54
View commit details
Copy full SHA for 4fdea54
Browse repository at this point
llama : enable LLAMA_SET_ROWS=1 by default (#14959)
Show description for a4569c4
ggerganov
authored
a4569c4
View commit details
Copy full SHA for a4569c4
Browse repository at this point
cuda, sycl : fix batched gemm when ne02 == 1 && ne03 > 1 (#15038)
Show description for 15e92fd
ggerganov
authored
15e92fd
View commit details
Copy full SHA for 15e92fd
Browse repository at this point
ci : check that pre-tokenizer hashes are up-to-date (#15032)
Show description for 2bf3fbf
CISC
authored
2bf3fbf
View commit details
Copy full SHA for 2bf3fbf
Browse repository at this point
convert : fix Qwen3-Embedding pre-tokenizer hash (#15030)
iamlemec
authored
711d5e6
View commit details
Copy full SHA for 711d5e6
Browse repository at this point
chat : fix multiple tool_calls on hermes-2-pro (#14962)
jhen0409
authored
f738989
View commit details
Copy full SHA for f738989
Browse repository at this point
vulkan: coopmat2 mul_mat optimizations (#14934)
Show description for 4cb208c
jeffbolznv
authored
4cb208c
View commit details
Copy full SHA for 4cb208c
Browse repository at this point
llama-bench: rename DB table name from test to llama_bench (#15003)
Show description for 3025b62
yeahdongcn
authored
3025b62
View commit details
Copy full SHA for 3025b62
Browse repository at this point
vulkan: Support ne[3]>1 in noncontig matrix-vector multiply (#15015)
jeffbolznv
authored
ec0b188
View commit details
Copy full SHA for ec0b188
Browse repository at this point
model : support Qwen3-Embedding (#15023)
iamlemec
authored
339bd02
View commit details
Copy full SHA for 339bd02
Browse repository at this point
server: enable token array inputs for OAI API (#15001)
JohannesGaessler
authored
f906275
View commit details
Copy full SHA for f906275
Browse repository at this point
vulkan: optimizations for direct convolution (#14933)
Show description for a9f7541
jeffbolznv
and
0cc4m
authored
a9f7541
View commit details
Copy full SHA for a9f7541
Browse repository at this point
Commits on Aug 1, 2025
CUDA: fix MMQ nwarps for AMD with warp_size==32 (#15014)
JohannesGaessler
authored
9c35706
View commit details
Copy full SHA for 9c35706
Browse repository at this point
vendor : update vendored copy of google/minja (#15011)
Show description for c76b420
l-austenfeld
authored
c76b420
View commit details
Copy full SHA for c76b420
Browse repository at this point
model : add hunyuan dense (#14878)
Show description for 0f5ccd6
stevenkuang-tencent
authored
0f5ccd6
View commit details
Copy full SHA for 0f5ccd6
Browse repository at this point
opencl: add f16 for `add`, `sub`, `mul`, `div` (#14984)
lhez
authored
1c872f7
View commit details
Copy full SHA for 1c872f7
Browse repository at this point
ggml : Q2k interleaving implementation - x86/x64 SIMD (#14373)
Show description for baad948
Srihari-mcw
and
Manogna-Sree
authored
baad948
View commit details
Copy full SHA for baad948
Browse repository at this point
graph : fix equal_seq() check (#14986)
Show description for ba42794
ggerganov
authored
ba42794
View commit details
Copy full SHA for ba42794
Browse repository at this point
docker : add cann build pipline (#14591)
Show description for 2860d47
3 people
authored
2860d47
View commit details
Copy full SHA for 2860d47
Browse repository at this point
compare-commits.sh: support both llama-bench and test-backend-ops (#14392)
Show description for 484b209
yeahdongcn
and
JohannesGaessler
authored
484b209
View commit details
Copy full SHA for 484b209
Browse repository at this point
Commits on Jul 31, 2025
quantize : skip tensor override when in fallback mode (#14995)
EAddario
authored
daf2dd7
View commit details
Copy full SHA for daf2dd7
Browse repository at this point
llama : add simple option to enable CPU for MoE weights (--cpu-moe) (#14992)
slaren
authored
a06ed5f
View commit details
Copy full SHA for a06ed5f
Browse repository at this point
Fix params bug in diffusion example (#14993)
am17an
authored
7845240
View commit details
Copy full SHA for 7845240
Browse repository at this point
llama : allow other bufts when overriding to CPU, add --no-repack option (#14990)
slaren
authored
d6818d0
View commit details
Copy full SHA for d6818d0
Browse repository at this point
Vulkan: Fix minor debug mode issues (#14899)
Show description for e08a988
0cc4m
authored
e08a988
View commit details
Copy full SHA for e08a988
Browse repository at this point
Previous
Next
You can’t perform that action at this time.
