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 }}
daeinki
llama.cpp
Repository navigation
Code
Pull requests
Actions
Projects
Security and quality
Insights
More
items
Commits
Branch selector
master
User selector
All users
Datepicker
All time
Commit history
Commits on Jan 17, 2024
sync : ggml
ggerganov
committed
6b6916b
View commit details
Copy full SHA for 6b6916b
Browse repository at this point
ggml : add IQ2 to test-backend-ops + refactoring (#4990)
Show description for 3856668
ggerganov
authored
3856668
View commit details
Copy full SHA for 3856668
Browse repository at this point
imatrix : offload to GPU support (#4957)
Show description for ba69bbc
ggerganov
authored
ba69bbc
View commit details
Copy full SHA for ba69bbc
Browse repository at this point
backend : add eval callback (#4935)
Show description for 44a1a4a
ggerganov
authored
44a1a4a
View commit details
Copy full SHA for 44a1a4a
Browse repository at this point
metal : create autorelease pool during library build (#4970)
Show description for c918fe8
ggerganov
authored
c918fe8
View commit details
Copy full SHA for c918fe8
Browse repository at this point
py : fix whitespace
ggerganov
committed
0f83e72
View commit details
Copy full SHA for 0f83e72
Browse repository at this point
py : fix missing added_tokens_dict for SPM and BPE vocabs (#4971)
Show description for 4f4bf35
ggerganov
authored
4f4bf35
View commit details
Copy full SHA for 4f4bf35
Browse repository at this point
llama : use Q4_K for attn_v for Q2_K_S when n_gqa >= 4 (#4996)
Show description for 2b3a665
ikawrakow
and
Iwan Kawrakow
authored
2b3a665
View commit details
Copy full SHA for 2b3a665
Browse repository at this point
metal : remove unnecessary nil check (#4986)
ptsochantaris
authored
7563293
View commit details
Copy full SHA for 7563293
Browse repository at this point
llama : fix copy/paste error in llama_sampling_params comment (#4994)
dwrensha
authored
f46c0c1
View commit details
Copy full SHA for f46c0c1
Browse repository at this point
Commits on Jan 16, 2024
py : remove unnecessary hasattr (#4903)
ggerganov
committed
5c99960
View commit details
Copy full SHA for 5c99960
Browse repository at this point
nix: remove nixConfig from flake.nix (#4984)
philiptaron
authored
bee938d
View commit details
Copy full SHA for bee938d
Browse repository at this point
finetune : add training data file to log message (#4979)
Show description for cec8a48
danbev
authored
cec8a48
View commit details
Copy full SHA for cec8a48
Browse repository at this point
ggml : importance matrix support for legacy quants (#4969)
Show description for 334a835
ikawrakow
and
Iwan Kawrakow
authored
334a835
View commit details
Copy full SHA for 334a835
Browse repository at this point
examples : add complete parallel function calling example (#4974)
Maximilian-Winter
authored
4feb4b3
View commit details
Copy full SHA for 4feb4b3
Browse repository at this point
perplexity : fix kv cache handling for hellaswag (#4981)
Show description for 959ef0c
ggerganov
authored
959ef0c
View commit details
Copy full SHA for 959ef0c
Browse repository at this point
flake.lock: update flake-parts, flake-parts/nixpkgs-lib, and nixpkgs (#4920)
Show description for c37b347
ggerganov
and
github-actions[bot]
authored
c37b347
View commit details
Copy full SHA for c37b347
Browse repository at this point
metal : localized logic in `ggml_metal_graph_compute` (#4924)
Show description for 158f8c9
ptsochantaris
authored
158f8c9
View commit details
Copy full SHA for 158f8c9
Browse repository at this point
android : introduce starter project example (#4926)
Show description for 862f5e4
luciferous
authored
862f5e4
View commit details
Copy full SHA for 862f5e4
Browse repository at this point
metal : replace loop of dispatch_async with dispatch_apply (#4934)
Show description for 3a48d55
azarovalex
and
ggerganov
authored
3a48d55
View commit details
Copy full SHA for 3a48d55
Browse repository at this point
metal : log `recommendedMaxWorkingSetSize` on iOS 16+ (#4936)
Show description for 7c8d3ab
azarovalex
and
ggerganov
authored
7c8d3ab
View commit details
Copy full SHA for 7c8d3ab
Browse repository at this point
examples : fix and improv docs for the grammar generator (#4909)
Show description for 122ed48
Maximilian-Winter
authored
122ed48
View commit details
Copy full SHA for 122ed48
Browse repository at this point
ggml : introduce GGML_CALL function annotation (#4850)
Show description for a0b3ac8
jart
authored
a0b3ac8
View commit details
Copy full SHA for a0b3ac8
Browse repository at this point
finetune : use LLAMA_FILE_MAGIC_GGLA (#4961)
Show description for d75c232
danbev
authored
d75c232
View commit details
Copy full SHA for d75c232
Browse repository at this point
speculative : threading options (#4959)
Show description for e032428
stduhpf
authored
e032428
View commit details
Copy full SHA for e032428
Browse repository at this point
Commits on Jan 15, 2024
pass cpu-architecture arguments only to host code (C;C++) (#4943)
ngc92
authored
3e5ca79
View commit details
Copy full SHA for 3e5ca79
Browse repository at this point
llama : apply classifier-free guidance to logits directly (#4951)
dfriehs
authored
4483396
View commit details
Copy full SHA for 4483396
Browse repository at this point
awq-py : fix typo in awq-py/README.md (#4947)
ziliangpeng
authored
d9aa4ff
View commit details
Copy full SHA for d9aa4ff
Browse repository at this point
cuda : fix dequantize kernel names (#4938)
ggerganov
committed
ddb008d
View commit details
Copy full SHA for ddb008d
Browse repository at this point
llama : check for 256 divisibility for IQ2_XS, IQ2_XXS (#4950)
Show description for 2faaef3
ikawrakow
and
Iwan Kawrakow
authored
2faaef3
View commit details
Copy full SHA for 2faaef3
Browse repository at this point
CUDA: faster dequantize kernels for Q4_0 and Q4_1 (#4938)
Show description for 4a3156d
ikawrakow
and
Iwan Kawrakow
authored
4a3156d
View commit details
Copy full SHA for 4a3156d
Browse repository at this point
Commits on Jan 14, 2024
llama : fix missing quotes (#4937)
David Pflug
authored
a836c8f
View commit details
Copy full SHA for a836c8f
Browse repository at this point
Add ability to use importance matrix for all k-quants (#4930)
Show description for 467a882
ikawrakow
and
Iwan Kawrakow
authored
467a882
View commit details
Copy full SHA for 467a882
Browse repository at this point
llama : check LLAMA_TRACE env for extra logging (#4929)
Show description for bb0c139
ggerganov
authored
bb0c139
View commit details
Copy full SHA for bb0c139
Browse repository at this point
scripts : sync-ggml-am.sh option to skip commits
ggerganov
committed
9408cfd
View commit details
Copy full SHA for 9408cfd
Browse repository at this point
Previous
Next
You can’t perform that action at this time.