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 }}
AlbertoSono
/
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 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
Commits on Jul 8, 2025
Sync abetlen/llama-cpp-python 0.3.12 code
JamePeng
committed
c7a1e13
View commit details
Copy full SHA for c7a1e13
View code at this point
Browse repository at this point
Commits on Jul 6, 2025
Sync abetlen/llama-cpp-python 0.3.11 code
JamePeng
committed
0701c73
View commit details
Copy full SHA for 0701c73
View code at this point
Browse repository at this point
Commits on Jun 20, 2025
modify setup-msbuild@v2 remove vs-version
JamePeng
committed
40f3403
View commit details
Copy full SHA for 40f3403
View code at this point
Browse repository at this point
Commits on Jun 10, 2025
pin gh-release action to v2.2.2
JamePeng
committed
3e0bb66
View commit details
Copy full SHA for 3e0bb66
View code at this point
Browse repository at this point
Commits on Jun 3, 2025
Fixed Jimver/cuda-toolkit last normal version 0.2.23
JamePeng
committed
5b63721
View commit details
Copy full SHA for 5b63721
View code at this point
Browse repository at this point
Commits on May 20, 2025
build-wheels-linux -DCMAKE_CUDA_ARCHITECTURES add 70-real;75-real
JamePeng
committed
c785a54
View commit details
Copy full SHA for c785a54
View code at this point
Browse repository at this point
Commits on May 4, 2025
Update Submodule vendor/llama.cpp e1e8e09..8ae5ebc
JamePeng
committed
2e89e3f
View commit details
Copy full SHA for 2e89e3f
View code at this point
Browse repository at this point
Commits on May 3, 2025
Split cu124 and cu126 build-wheels-linux.yml:
Show description for 623f7ed
JamePeng
committed
623f7ed
View commit details
Copy full SHA for 623f7ed
View code at this point
Browse repository at this point
Try to enable LLAVA_BUILD in build-wheels-cuda-linux.yml
JamePeng
committed
c108044
View commit details
Copy full SHA for c108044
View code at this point
Browse repository at this point
Commits on May 2, 2025
Upload build-wheels-cuda-linux.yml
JamePeng
committed
786d15c
View commit details
Copy full SHA for 786d15c
View code at this point
Browse repository at this point
Commits on May 1, 2025
Update build-wheels-cuda-win.yml: use astral-sh/setup-uv@v6 for setup-uv option
JamePeng
committed
b0ea709
View commit details
Copy full SHA for b0ea709
View code at this point
Browse repository at this point
Commits on Apr 8, 2025
add -DLLAMA_CURL=OFF cmake arg avoid the the error "Could NOT find CURL"
JamePeng
committed
a505718
View commit details
Copy full SHA for a505718
View code at this point
Browse repository at this point
Commits on Mar 18, 2025
Build Wheels (CUDA) for Windows workflow append build date tag
JamePeng
committed
b750a5f
View commit details
Copy full SHA for b750a5f
View code at this point
Browse repository at this point
Commits on Mar 13, 2025
Add new Build Wheels (CUDA) for Windows workflow
Show description for 37ae873
JamePeng
committed
37ae873
View commit details
Copy full SHA for 37ae873
View code at this point
Browse repository at this point
Commits on Jan 29, 2025
fix(ci): Fix the CUDA workflow (#1894)
oobabooga
authored
14879c7
View commit details
Copy full SHA for 14879c7
View code at this point
Browse repository at this point
Previous
Next
You can’t perform that action at this time.