ggml-org/llama.cpp · Architecture
A static read of how ggml-org/llama.cpp is wired together — module coupling, layering, and circular dependencies — derived from its import graph.
A
Architecture grade
score 89/100
1
Import cycles
lower is better
153
Modules parsed
139 edges
99%
Layeredness
clean-layer ratio
Most-depended-on modules
These are the highest-fan-in files — change them and the blast radius is largest. Read them first.
- conversion/base.py91 importers · radius 93
- conversion/llama.py15 importers · radius 19
- conversion/qwen.py8 importers · radius 15
- conversion/deepseek.py6 importers · radius 6
- conversion/__init__.py5 importers · radius 93
- conversion/qwenvl.py3 importers · radius 4
- conversion/llava.py2 importers · radius 3
- conversion/mamba.py2 importers · radius 3
Modules (3)
Source directories grouped from the import graph. Each links to a per-module page with its files and how it couples to the rest.
- conversion92 files · 138 in-degree · in cycle
- gguf-py/tests2 files · 1 in-degree
- (root)2 files · 0 in-degree
Circular dependencies (1)
- conversion/__init__.py to conversion/base.py to conversion/__init__.py
Ask AI about ggml-org/llama.cpp
Grounded in the actual source code. Pick a starter question or write your own.
What does this repo do, in one paragraph?How would I get started using it?What are the main alternatives?Show me the entry point.
Or write your own questionInformational only. RepoPilot summarises public signals at the time of analysis; they can be incomplete or stale. Not professional, security, or legal advice.