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 }}
dimitribarbot
/
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
Branch selector
main
User selector
All users
All time
Commit history
Commits on Apr 24, 2026
feat(speculative): introduce O(1) hash-based N-Gram speculative decoding
Show description for ddf577d
JamePeng
committed
ddf577d
View commit details
Copy full SHA for ddf577d
Browse repository at this point
Update Submodule vendor/llama.cpp 8bccdbb..13d36cf
JamePeng
committed
7a02d4d
View commit details
Copy full SHA for 7a02d4d
Browse repository at this point
Commits on Apr 22, 2026
Update /docs/wiki/core/Llama.md
Show description for 852a2e9
JamePeng
committed
852a2e9
View commit details
Copy full SHA for 852a2e9
Browse repository at this point
feat(types): introduce MCP definitions and align with latest OpenAI spec
Show description for afd038f
JamePeng
committed
afd038f
View commit details
Copy full SHA for afd038f
Browse repository at this point
Update Submodule vendor/llama.cpp 82209ef..8bccdbb
JamePeng
committed
dbb7407
View commit details
Copy full SHA for dbb7407
Browse repository at this point
Commits on Apr 21, 2026
Update Submodule vendor/llama.cpp 81df3f7..82209ef
JamePeng
committed
8625836
View commit details
Copy full SHA for 8625836
Browse repository at this point
Commits on Apr 20, 2026
Update Submodule vendor/llama.cpp 037bfe3..81df3f7
JamePeng
committed
e3b7ad6
View commit details
Copy full SHA for e3b7ad6
Browse repository at this point
Commits on Apr 19, 2026
docs: initialize LLM Wiki structure for better documentation maintenance
Show description for 15f8a36
JamePeng
committed
15f8a36
View commit details
Copy full SHA for 15f8a36
Browse repository at this point
Update Submodule vendor/llama.cpp 45cac7c..037bfe3
JamePeng
committed
3984ab5
View commit details
Copy full SHA for 3984ab5
Browse repository at this point
Commits on Apr 17, 2026
chore(ci): upgrade astral-sh/setup-uv@v7 and Jimver/
[email protected]
(Node 24 runtime)
JamePeng
committed
33ce052
View commit details
Copy full SHA for 33ce052
Browse repository at this point
Update Submodule vendor/llama.cpp 9db77a0..45cac7c
JamePeng
committed
7a19575
View commit details
Copy full SHA for 7a19575
Browse repository at this point
Commits on Apr 16, 2026
Bump version to 0.3.36
Show description for b97cb63
JamePeng
committed
b97cb63
View commit details
Copy full SHA for b97cb63
Browse repository at this point
feat: enhance Qwen35ChatHandler with preserve_thinking and Qwen3.6 template fixes
Show description for 7820677
JamePeng
committed
7820677
View commit details
Copy full SHA for 7820677
Browse repository at this point
Update Submodule vendor/llama.cpp 8dc530b..9db77a0
JamePeng
committed
9e00017
View commit details
Copy full SHA for 9e00017
Browse repository at this point
chore(ci): upgrade softprops/action-gh-release to v3 (Node 24 runtime)
JamePeng
committed
3ee7ff8
View commit details
Copy full SHA for 3ee7ff8
Browse repository at this point
Commits on Apr 15, 2026
Sync mtmd: add mtmd_image_tokens_get_decoder_pos() API (#21851)
Show description for 9d2b2cb
JamePeng
committed
9d2b2cb
View commit details
Copy full SHA for 9d2b2cb
Browse repository at this point
Update Submodule vendor/llama.cpp 1f30ac0..8dc530b
JamePeng
committed
701195e
View commit details
Copy full SHA for 701195e
Browse repository at this point
Commits on Apr 14, 2026
docs: add comprehensive omni multimodal example for Gemma-4
Show description for 7115772
JamePeng
committed
7115772
View commit details
Copy full SHA for 7115772
Browse repository at this point
Update Submodule vendor/llama.cpp 75f3bc9..1f30ac0
JamePeng
committed
e70304b
View commit details
Copy full SHA for e70304b
Browse repository at this point
Commits on Apr 13, 2026
docs: add audio processing recommendation to Gemma4ChatHandler
Show description for 5e6529e
JamePeng
committed
5e6529e
View commit details
Copy full SHA for 5e6529e
Browse repository at this point
Update Submodule vendor/llama.cpp 073bb2c..75f3bc9
JamePeng
committed
4ec15ac
View commit details
Copy full SHA for 4ec15ac
Browse repository at this point
Commits on Apr 11, 2026
refactor: update Gemma4ChatHandler with latest google/gemma-4-31B-it chat template from huggingface
Show description for 122d8db
JamePeng
committed
122d8db
View commit details
Copy full SHA for 122d8db
Browse repository at this point
Update Submodule vendor/llama.cpp d132f22..073bb2c
JamePeng
committed
e73ad59
View commit details
Copy full SHA for e73ad59
Browse repository at this point
Commits on Apr 9, 2026
Update README.md for OpenVINO/Metal/Vulkan/SYCL
Show description for 634a712
JamePeng
committed
634a712
View commit details
Copy full SHA for 634a712
Browse repository at this point
fix missing change of llama_cpp.llama_split_mode.LLAMA_SPLIT_MODE_LAYER,
JamePeng
committed
f22b819
View commit details
Copy full SHA for f22b819
Browse repository at this point
Update Makefile
JamePeng
committed
7d2c4ba
View commit details
Copy full SHA for 7d2c4ba
Browse repository at this point
Sync ggml: backend-agnostic tensor parallelism (experimental) (#19378)
JamePeng
committed
6866eba
View commit details
Copy full SHA for 6866eba
Browse repository at this point
Update Submodule vendor/llama.cpp d12cc3d..d132f22
JamePeng
committed
5a47267
View commit details
Copy full SHA for 5a47267
Browse repository at this point
Commits on Apr 8, 2026
Implement `Step3VLChatHandler` for Step3-VL-10B
Show description for abe789f
JamePeng
committed
abe789f
View commit details
Copy full SHA for abe789f
Browse repository at this point
Sync ggml: add Q1_0 1-bit quantization support (CPU) (#21273)
JamePeng
committed
9241b0f
View commit details
Copy full SHA for 9241b0f
Browse repository at this point
Update Submodule vendor/llama.cpp 4eb1951..d12cc3d
Show description for 6ebab28
JamePeng
committed
6ebab28
View commit details
Copy full SHA for 6ebab28
Browse repository at this point
Commits on Apr 7, 2026
feat(types): align with latest OpenAI API spec and fix type issues
Show description for 645c8ed
JamePeng
committed
645c8ed
View commit details
Copy full SHA for 645c8ed
Browse repository at this point
Adding the `actions/checkout` step to the release job to provide the `.git` context required by the CLI's `--generate-notes` flag.
JamePeng
committed
fbbf2dd
View commit details
Copy full SHA for fbbf2dd
Browse repository at this point
Update Submodule vendor/llama.cpp 69c28f1..4eb1951
JamePeng
committed
58c5fe1
View commit details
Copy full SHA for 58c5fe1
Browse repository at this point
fix multi-line script in metal workflow
JamePeng
committed
e9c3013
View commit details
Copy full SHA for e9c3013
Browse repository at this point
Previous
Next
You can’t perform that action at this time.