Skip to content
Navigation Menu
Sign in
Products
Platform
GitHub
Repository hosting, code review, and collaboration
Copilot
AI coding agent for tasks, projects, and automated work
Build & Ship
Actions
CI/CD and automation
Code Quality
Quality analysis, fixes, and enforcement
Codespaces
Cloud development environments
Secure
Code Security
Vulnerability detection and remediation
Secret Protection
Secret scanning and leak prevention
All Features
Developers
Learn
Documentation
Training
Certifications
Build
Build with Copilot
Customize Copilot
Integrations
Explore
Trending repos
GitHub Sponsors
Developer articles
Changelog
Changelog
Your source for the latest features, improvements, and fixes across GitHub products, all in one place.
Businesses
By Stage
Enterprises
Team
Startups
Nonprofits
By Industry
Healthcare
Financial services
Manufacturing
Government
See all industries
Evaluate GitHub
Why GitHub
Customer Stories
Business insights
Trust Center
Add-ons
GitHub Advanced Security
Enterprise-grade code security
Copilot for business
Enterprise-grade AI features
Premium Support
Enterprise-grade 24/7 support
Resources
Learn & Connect
Documentation
Resource center
Blog
Events & webinars
Community Forum
Customer Stories
Integrations
Support
Customer support
Training
GitHub Status
Company
About
Partners
Changelog
GitHub Universe
GitHub Universe
The event for developers, by developers — talks, workshops, and what’s next for GitHub.
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 }}
tk-master
llama-cpp-python
Repository navigation
Code
Pull requests
Actions
Projects
Security and quality
Insights
More
items
Commits
Breadcrumbs
History for
llama-cpp-python
llama_cpp
llama.py
on
main
User selector
All users
Datepicker
All time
Commit history
Commits on Nov 16, 2023
Fix for negative temp (sample_softmax)
tk-master
committed
e2ab96a
View commit details
Copy full SHA for e2ab96a
View code at this point
Browse repository at this point
Added support for min_p
Show description for 1b1a918
tk-master
committed
1b1a918
View commit details
Copy full SHA for 1b1a918
View code at this point
Browse repository at this point
Commits on Nov 10, 2023
Fix sampling bug when logits_all=False
abetlen
committed
6f0b0b1
View commit details
Copy full SHA for 6f0b0b1
View code at this point
Browse repository at this point
Potential bugfix for eval
abetlen
committed
d9b38e3
View commit details
Copy full SHA for d9b38e3
View code at this point
Browse repository at this point
Fix: default max_tokens matches openai api (16 for completion, max length for chat completion)
abetlen
committed
e7962d2
View commit details
Copy full SHA for e7962d2
View code at this point
Browse repository at this point
Commits on Nov 8, 2023
Add set_seed to Llama class
abetlen
committed
fd41ed3
View commit details
Copy full SHA for fd41ed3
View code at this point
Browse repository at this point
Fix destructor NoneType is not callable error
abetlen
committed
ca4cb88
View commit details
Copy full SHA for ca4cb88
View code at this point
Browse repository at this point
Add JSON mode support. Closes #881
abetlen
committed
b30b9c3
View commit details
Copy full SHA for b30b9c3
View code at this point
Browse repository at this point
Add seed parameter support for completion and chat_completion requests. Closes #884
abetlen
committed
86aeb9f
View commit details
Copy full SHA for 86aeb9f
View code at this point
Browse repository at this point
Multimodal Support (Llava 1.5) (#821)
Show description for aab74f0
damian0815
and
abetlen
authored
aab74f0
View commit details
Copy full SHA for aab74f0
View code at this point
Browse repository at this point
Commits on Nov 6, 2023
Fix type bug
abetlen
committed
be0add1
View commit details
Copy full SHA for be0add1
View code at this point
Browse repository at this point
Refactor Llama class internals
abetlen
committed
e214a58
View commit details
Copy full SHA for e214a58
View code at this point
Browse repository at this point
Commits on Nov 3, 2023
Clean up stdout / stderr suppression
abetlen
committed
2ec043a
View commit details
Copy full SHA for 2ec043a
View code at this point
Browse repository at this point
Rename internal only module utils to _utils
abetlen
committed
4ea7027
View commit details
Copy full SHA for 4ea7027
View code at this point
Browse repository at this point
Update llama.cpp
abetlen
committed
df9362e
View commit details
Copy full SHA for df9362e
View code at this point
Browse repository at this point
Add functionary support (#784)
Show description for 3af7b21
abetlen
authored
3af7b21
View commit details
Copy full SHA for 3af7b21
View code at this point
Browse repository at this point
Migrate inference to llama_batch and llama_decode api (#795)
Show description for ab028cb
abetlen
and
antoine-lizee
authored
ab028cb
View commit details
Copy full SHA for ab028cb
View code at this point
Browse repository at this point
Commits on Nov 2, 2023
Update llama.cpp
Show description for fa83cc5
abetlen
committed
fa83cc5
View commit details
Copy full SHA for fa83cc5
View code at this point
Browse repository at this point
fix: tokenization of special characters: (#850)
Show description for 4d4e0f1
antoine-lizee
authored and
abetlen
committed
4d4e0f1
View commit details
Copy full SHA for 4d4e0f1
View code at this point
Browse repository at this point
Commits on Nov 1, 2023
llama: fix exception in Llama.__del__ (#846)
cebtenzzre
authored
eefd76f
View commit details
Copy full SHA for eefd76f
View code at this point
Browse repository at this point
fixed Llama._create_completion suffix check, it can be either None or str instance (#854)
mtasic85
authored
9c8f4dc
View commit details
Copy full SHA for 9c8f4dc
View code at this point
Browse repository at this point
Commits on Oct 24, 2023
Update llama.cpp
abetlen
committed
53861c9
View commit details
Copy full SHA for 53861c9
View code at this point
Browse repository at this point
Commits on Oct 19, 2023
Fix streaming doesn't return finish reason (#798)
Show description for 09a8406
gmcgoldr
authored
09a8406
View commit details
Copy full SHA for 09a8406
View code at this point
Browse repository at this point
Update llama.cpp
abetlen
committed
ff58003
View commit details
Copy full SHA for ff58003
View code at this point
Browse repository at this point
Commits on Oct 15, 2023
Make use of suppress_stdout_stderr when freeing model (#803)
paschembri
authored
10304d7
View commit details
Copy full SHA for 10304d7
View code at this point
Browse repository at this point
Add validation for tensor_split size exceeding LLAMA_MAX_DEVICES (#820)
Show description for b501665
eric1932
authored
b501665
View commit details
Copy full SHA for b501665
View code at this point
Browse repository at this point
Commits on Sep 30, 2023
Fix logits_all bug
abetlen
committed
d696251
View commit details
Copy full SHA for d696251
View code at this point
Browse repository at this point
Fix bug in embedding
abetlen
committed
42bb721
View commit details
Copy full SHA for 42bb721
View code at this point
Browse repository at this point
Commits on Sep 29, 2023
Configurable Chat Formats (#711)
Show description for 3bca770
abetlen
authored
3bca770
View commit details
Copy full SHA for 3bca770
View code at this point
Browse repository at this point
Fix rope scaling defaults (#767)
Show description for a945404
Josh-XT
authored
a945404
View commit details
Copy full SHA for a945404
View code at this point
Browse repository at this point
Update llama.cpp
abetlen
committed
1a1c3dc
View commit details
Copy full SHA for 1a1c3dc
View code at this point
Browse repository at this point
Commits on Sep 18, 2023
Update llama.cpp
abetlen
committed
38e34c9
View commit details
Copy full SHA for 38e34c9
View code at this point
Browse repository at this point
Commits on Sep 14, 2023
Add numa support, low level api users must now explicitly call llama_backend_init at the start of their programs.
abetlen
committed
f4090a0
View commit details
Copy full SHA for f4090a0
View code at this point
Browse repository at this point
Reorder init params to match llama.cpp order
abetlen
committed
6a20293
View commit details
Copy full SHA for 6a20293
View code at this point
Browse repository at this point
Explicitly make all init params other than model_path into keyword only params
abetlen
committed
c8f9b8a
View commit details
Copy full SHA for c8f9b8a
View code at this point
Browse repository at this point
Previous
Next
You can’t perform that action at this time.