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
.
cosmasense
/
llama-cpp-python
Public
forked from
JamePeng/llama-cpp-python
Notifications
You must be signed in to change notification settings
Fork
0
Star
0
Code
Pull requests
0
Actions
Projects
Security and quality
0
Insights
Additional navigation options
Code
Pull requests
Actions
Projects
Security and quality
Insights
Commits
Breadcrumbs
History for
llama-cpp-python
.github
on
main
User selector
All users
All time
Commit history
Commits on Apr 16, 2026
Add PEP 503 simple index workflow
Show description for ff98e3f
chmltn
and
claude
committed
ff98e3f
View commit details
Copy full SHA for ff98e3f
View code at this point
Browse repository at this point
Commits on Mar 13, 2026
Update Metal wheel workflow: trigger on tags, build cp312+cp313
Show description for 2378cfb
chmltn
and
claude
committed
2378cfb
View commit details
Copy full SHA for 2378cfb
View code at this point
Browse repository at this point
Commits on Mar 8, 2026
docs(issue-template): modernize bug report for efficiency
Show description for 8ec1763
JamePeng
committed
8ec1763
View commit details
Copy full SHA for 8ec1763
View code at this point
Browse repository at this point
Commits on Feb 20, 2026
fix typo in metal workflow
JamePeng
committed
3d0fd1b
View commit details
Copy full SHA for 3d0fd1b
View code at this point
Browse repository at this point
Commits on Feb 16, 2026
Sync build : remove LLAMA_HTTPLIB option
JamePeng
committed
4b13964
View commit details
Copy full SHA for 4b13964
View code at this point
Browse repository at this point
Commits on Feb 12, 2026
Remove outdated workflow
JamePeng
committed
a3cf5c3
View commit details
Copy full SHA for a3cf5c3
View code at this point
Browse repository at this point
ci: use llama_cpp.__version__ for release tagging and fix cross-job version propagation
JamePeng
committed
a7f96a5
View commit details
Copy full SHA for a7f96a5
View code at this point
Browse repository at this point
Commits on Feb 11, 2026
Refactor the build-wheels-metal.yaml
JamePeng
committed
2b6d470
View commit details
Copy full SHA for 2b6d470
View code at this point
Browse repository at this point
Commits on Feb 9, 2026
test: update integration tests for new sampler architecture
Show description for 31a9d73
JamePeng
committed
31a9d73
View commit details
Copy full SHA for 31a9d73
View code at this point
Browse repository at this point
Commits on Feb 8, 2026
fix cu130 workflow typo
JamePeng
committed
4ab1823
View commit details
Copy full SHA for 4ab1823
View code at this point
Browse repository at this point
build: expand non-AVX flags for Basic build compatibility
Show description for acb7efa
JamePeng
committed
acb7efa
View commit details
Copy full SHA for acb7efa
View code at this point
Browse repository at this point
Commits on Jan 29, 2026
fix: Append missing abi_tag
JamePeng
committed
f3b31ae
View commit details
Copy full SHA for f3b31ae
View code at this point
Browse repository at this point
Commits on Jan 27, 2026
ci: Customize wheel filename to improve version identification
Show description for 6c536a0
JamePeng
committed
6c536a0
View commit details
Copy full SHA for 6c536a0
View code at this point
Browse repository at this point
Adding Python 3.14 to the GitHub action workflow
Show description for f7e5307
JamePeng
committed
f7e5307
View commit details
Copy full SHA for f7e5307
View code at this point
Browse repository at this point
Commits on Jan 22, 2026
Simplify test.yaml and add tests for Python 3.14.
JamePeng
committed
02ae101
View commit details
Copy full SHA for 02ae101
View code at this point
Browse repository at this point
Commits on Dec 9, 2025
Attempting to fix the AVX2 workflow: Missing GGML_FMA and GGML_F16C may cause an OSError: [WinError -1073741795] Windows Error 0xc000001d error on processors that support AVX2 instructions.
JamePeng
committed
fcfde24
View commit details
Copy full SHA for fcfde24
View code at this point
Browse repository at this point
Commits on Dec 7, 2025
workflow: Fixed nvcc fatal : Unsupported gpu architecture 'compute_101'
JamePeng
committed
4189786
View commit details
Copy full SHA for 4189786
View code at this point
Browse repository at this point
workflow: Added workflows for compiling with CUDA 13.0.2 on Windows and Linux.
JamePeng
committed
2b97b7e
View commit details
Copy full SHA for 2b97b7e
View code at this point
Browse repository at this point
Remove outdated CUDA workflows
JamePeng
committed
61e2346
View commit details
Copy full SHA for 61e2346
View code at this point
Browse repository at this point
Commits on Dec 2, 2025
Fixed Basic workflow typos
JamePeng
committed
5d49287
View commit details
Copy full SHA for 5d49287
View code at this point
Browse repository at this point
Add new workflow with Basic options for Linux platform (CUDA 12.4, 12.6, 12.8)
JamePeng
committed
22034f5
View commit details
Copy full SHA for 22034f5
View code at this point
Browse repository at this point
Commits on Nov 21, 2025
Sync cmake : add option to build and link BoringSSL and OpenSSL
JamePeng
committed
01ed775
View commit details
Copy full SHA for 01ed775
View code at this point
Browse repository at this point
Commits on Nov 17, 2025
Add a Basic workflow for cu128 windows wheels
JamePeng
committed
cfb4f8f
View commit details
Copy full SHA for cfb4f8f
View code at this point
Browse repository at this point
Commits on Nov 12, 2025
Use httplib to download model from an URL when the libcurl is disabled
Show description for 4e901b7
JamePeng
committed
4e901b7
View commit details
Copy full SHA for 4e901b7
View code at this point
Browse repository at this point
Commits on Nov 10, 2025
Refining the AVX instruction compilation workflow
JamePeng
committed
dd38ec6
View commit details
Copy full SHA for dd38ec6
View code at this point
Browse repository at this point
Commits on Nov 9, 2025
Adding workflow compilation options for platforms without AVX instructions or AVXVNNI instruction can be achieved by setting the releasetag parameter above to Basic/AVXVNNI.
Show description for 5abcf51
JamePeng
committed
5abcf51
View commit details
Copy full SHA for 5abcf51
View code at this point
Browse repository at this point
Commits on Nov 3, 2025
Optimize Windows CUDA Wheel Build Workflow
Show description for c008d9e
JamePeng
committed
c008d9e
View commit details
Copy full SHA for c008d9e
View code at this point
Browse repository at this point
Commits on Oct 23, 2025
Separate cu128 compilation from the windows github action and supplement sm_87 sm101 compilation
JamePeng
committed
4f98b28
View commit details
Copy full SHA for 4f98b28
View code at this point
Browse repository at this point
Use the N-Storm/cuda-toolkit instead of Jimver/cuda-toolkit
JamePeng
committed
6ec4e64
View commit details
Copy full SHA for 6ec4e64
View code at this point
Browse repository at this point
Commits on Sep 24, 2025
Adjust test.yaml to macos14
JamePeng
committed
94e8eb5
View commit details
Copy full SHA for 94e8eb5
View code at this point
Browse repository at this point
Fixed the huggingface_hub command error
JamePeng
committed
128e23c
View commit details
Copy full SHA for 128e23c
View code at this point
Browse repository at this point
Commits on Sep 13, 2025
Simplify the code structure of test.yaml
JamePeng
committed
44e5534
View commit details
Copy full SHA for 44e5534
View code at this point
Browse repository at this point
Commits on Aug 21, 2025
Try to add python3.13 version compilation
JamePeng
committed
62bea58
View commit details
Copy full SHA for 62bea58
View code at this point
Browse repository at this point
Commits on Aug 1, 2025
Remove sm_70 in cuda12.8.1 action flow
JamePeng
committed
fcbb32e
View commit details
Copy full SHA for fcbb32e
View code at this point
Browse repository at this point
Try to compile with cuda12.8.1 for Blackwell architecture (sm_100 and sm_120) computing cards
JamePeng
committed
a617e31
View commit details
Copy full SHA for a617e31
View code at this point
Browse repository at this point
Previous
Next
You can’t perform that action at this time.