Home/Model Training/ggml

ggml

ggml-org/ggml

Tensor library for machine learning

GitHub

GraphCanon updated 4d · GitHub synced 4d · 28 views this month

15k stars1.8k forksLast push 1w C++ MIT

Decision brief

ggml is a C++ based tensor library that supports automatic-differentiation and large-language-models, making it suitable for performance-critical applications where language flexibility and low-level control are key.

Good fit when

- When you need to work with large language models or require automatic differentiation capabilities in your machine learning projects specifically within the C++ ecosystem
- If you seek high-performance computing with low-overhead due to ggml's focus on efficient tensor operations managed through its robust infrastructure

Avoid when

- Avoid if your project requires a more extensive set of tools and ease-of-use found in higher-level frameworks (e.g., TensorFlow or PyTorch)
- If you prefer environments where the majority of community support and libraries are available in Python rather than C++

Pricing:: freemium - Free to use with optional support or consulting services that can be sought from contributors or third parties.
Requirements:: Requires setting up a Python virtual environment and installing dependencies, as per provided README instructions; however, this is for interfacing with the C++; core does not affect its use in C++ projects.

Observed Jul 11, 2026 · Source: enrich:decision_facts

ggml alternatives Trust report

Verify the decision

Maintenance and security

Full trust report

Maintenance: Very active (2d since push); As of 4d
Provenance: Not a fork · Organization account; As of 4d
Security (OSV): 14 low (14 low); As of 1mo

Public GitHub metadata and optional OSV scans. Signals, not a guarantee. Trust methodology.

Backing

Company context for ggml. Display-only - separate from trust and ranking.

Company: ggml·GitHub org profile·1mo
Commercial model: Pure OSS·GitHub org profile (public repos)·1mo

Install

git clone https://github.com/ggml-org/ggml

How it fits your stack(4)

Typed graph edges - alternatives, integrations, successors, and dependencies. Ranked by relationship type, not raw GitHub stars.

Integrates

vllm

ggml, as a tensor library for machine learning with support for automatic differentiation and optimized runtime operations, can integrate with vLLM by providing the underlying tensor computation capabilities that vLLM utilizes to perform fast and memory-efficient inference tasks on large language models.

integrates

Depends on

transformers

Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models

depends on

LLMs-from-scratch

ggml could be used as a foundational component in building machine learning models from scratch, such as in rasbt's LLMs-from-scratch project.

depends on

paddler

Open-source LLM/VLM load balancer and serving platform for self-hosting at scale

used by

Relationship graph

Optional deeper exploration of typed edges and category neighbours.

vllm88k★

transformers164k★

LLMs-from-scratch103k★

IntegratesDepends onRelated

vllm88k★

transformers164k★

LLMs-from-scratch103k★

IntegratesDepends onRelated

Similar tools

Same-category neighbours not already linked as typed edges.

tensorflow

An Open Source Machine Learning Framework for Everyone

197k★

llama.cpp

LLM inference in C/C++

123k★

gpt4all

Run Local LLMs on Any Device

77k★

Evidence and technical details

Sourced facts, taxonomy, compatibility claims, README excerpt, and machine-readable endpoints.

Overview

ggml-org/ggml is a C++ based tensor library supporting automatic-differentiation and large-language-models.

Capability facts

Languages: c++
Source: github.language · Aug 17, 2026

Graph entities

ggmlcompany

Compatibility

Sourced claims from the README excerpt - not unsourced marketing copy.

Python runtimePython

Source: README excerpt (regex_v1, Aug 17, 2026)

# install python dependencies in a virtual environment

Source link

README

install python dependencies in a virtual environment

python3.10 -m venv .venv source .venv/bin/activate pip install -r requirements.txt

For agents

This page has a .md twin and JSON over the API.

/tools/ggml-org-ggml.md GET /api/graphcanon/tools/ggml-org-ggml GET /api/graphcanon/graph?tool=ggml-org-ggml