ggml-org/ggml
Tensor library for machine learning
Supports integer quantization and automatic differentiation with zero runtime memory allocations, enabling efficient inference and training across diverse hardware. Built as a low-level C library with no external dependencies, featuring ADAM and L-BFGS optimizers. Actively powers language model implementations like llama.cpp and whisper.cpp through a standardized GGUF file format.
14,217 stars. Actively maintained with 185 commits in the last 30 days.
Stars
14,217
Forks
1,511
Language
C++
License
MIT
Category
Last pushed
Feb 27, 2026
Commits (30d)
185
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/llm-tools/ggml-org/ggml"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related tools
onnx/ir-py
Efficient in-memory representation for ONNX, in Python
SandAI-org/MagiCompiler
A plug-and-play compiler that delivers free-lunch optimizations for both inference and training.
bytedance/lightseq
LightSeq: A High Performance Library for Sequence Processing and Generation
R-D-BioTech-Alaska/Qelm
Qelm - Quantum Enhanced Language Model
kekzl/imp
High-performance LLM inference engine in C++/CUDA for NVIDIA Blackwell GPUs (RTX 5090)