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 }}
ngxson
/
llama.cpp
Public
forked from
ggml-org/llama.cpp
Notifications
You must be signed in to change notification settings
Fork
5
Star
18
Code
Pull requests
65
Actions
Projects
Security and quality
0
Insights
Additional navigation options
Code
Pull requests
Actions
Projects
Security and quality
Insights
(MIRROR) Implement gguf init from buffer
- #104
#104
Open
ngxson
wants to merge 14 commits into
ngxson:master
ngxson/llama.cpp:master
from
giladgd:implementGgufInitFromBuffer
giladgd/llama.cpp:implementGgufInitFromBuffer
Copy head branch name to clipboard
Conversation
Commits
14
(14)
Checks
Files changed
Open
(MIRROR) Implement gguf init from buffer
#104
ngxson
wants to merge 14 commits into
ngxson:master
ngxson/llama.cpp:master
from
giladgd:implementGgufInitFromBuffer
giladgd/llama.cpp:implementGgufInitFromBuffer
Copy head branch name to clipboard
Commits
Commits on Apr 24, 2026
ggml: implement `gguf_init_from_buffer`
giladgd
committed
9b2aa8c
View commit details
Copy full SHA for 9b2aa8c
Browse repository at this point
test: `gguf_init_from_buffer`
giladgd
committed
de9ebec
View commit details
Copy full SHA for de9ebec
Browse repository at this point
Commits on Apr 25, 2026
fix: memory breakdown for a model loaded with `no_alloc` from a file is consistent with being loaded from a buffer
giladgd
committed
59883b3
View commit details
Copy full SHA for 59883b3
Browse repository at this point
fix: use `GGML_UNUSED`
Show description for 5950daa
giladgd
and
Copilot
committed
5950daa
View commit details
Copy full SHA for 5950daa
Browse repository at this point
Commits on Apr 27, 2026
fix: remove `total_size` from `gguf_reader`
giladgd
committed
b120c9b
View commit details
Copy full SHA for b120c9b
Browse repository at this point
fix: file offset calculation, rename `offset` to `data_offset`
Show description for 65f7136
giladgd
and
Copilot
committed
65f7136
View commit details
Copy full SHA for 65f7136
Browse repository at this point
refactor: extract model loader bug fixes to another PR
giladgd
committed
0a59d4e
View commit details
Copy full SHA for 0a59d4e
Browse repository at this point
Commits on Apr 28, 2026
feat: add `gguf_init_from_callback`
giladgd
committed
62f4e95
View commit details
Copy full SHA for 62f4e95
Browse repository at this point
fix: always require a max expected size
giladgd
committed
78bff38
View commit details
Copy full SHA for 78bff38
Browse repository at this point
fix: change `gguf_reader_callback_t`'s `output` type to `void *`, change `max_expected_size` and offsets to `uint64_t`
giladgd
committed
dcca71d
View commit details
Copy full SHA for dcca71d
Browse repository at this point
fix: harden against offset overflow in buffer read
giladgd
committed
6248d3c
View commit details
Copy full SHA for 6248d3c
Browse repository at this point
Commits on May 21, 2026
fix: remove seek behavior from the callback
giladgd
committed
913a28f
View commit details
Copy full SHA for 913a28f
Browse repository at this point
Commits on May 23, 2026
feat: `max_chunk_read == 0` means `SIZE_MAX`
giladgd
committed
7157cc0
View commit details
Copy full SHA for 7157cc0
Browse repository at this point
Commits on May 24, 2026
fix: seeking in a gguf file with no tensors
giladgd
committed
5908c58
View commit details
Copy full SHA for 5908c58
Browse repository at this point
You can’t perform that action at this time.