ggml-org/ggml
Tensor library for machine learning
This is a low-level tensor library for machine learning, enabling developers to implement and run machine learning models efficiently across various hardware. It takes model architectures and data, processing them into optimized computations for model inference and training. It's designed for machine learning engineers and developers who need fine-grained control over model deployment and performance.
14,217 stars. Actively maintained with 116 commits in the last 30 days.
Use this if you are a developer looking to build and deploy machine learning models with minimal dependencies and optimized performance on diverse hardware.
Not ideal if you are an end-user looking for a high-level, ready-to-use machine learning application or a data scientist who prefers common, high-level ML frameworks like TensorFlow or PyTorch.
Stars
14,217
Forks
1,511
Language
C++
License
MIT
Category
Last pushed
Feb 27, 2026
Commits (30d)
116
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/transformers/ggml-org/ggml"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Recent Releases
Related models
quic/efficient-transformers
This library empowers users to seamlessly port pretrained models and checkpoints on the...
ManuelSLemos/RabbitLLM
Run 70B+ LLMs on a single 4GB GPU — no quantization required.
SandAI-org/MagiCompiler
A plug-and-play compiler that delivers free-lunch optimizations for both inference and training.
alpa-projects/alpa
Training and serving large-scale neural networks with auto parallelization.
bytedance/lightseq
LightSeq: A High Performance Library for Sequence Processing and Generation