#cplusplus #automatic_differentiation #large_language_models #machine_learning #tensor_algebra
GGML is a lightweight, efficient tensor library written in C that helps you run large machine learning models on everyday hardware like laptops, phones, and even Raspberry Pi. It supports integer quantization (reducing model size and speeding up processing), automatic differentiation, and works across many platforms without needing extra software. GGML uses zero memory allocation during runtime, which improves performance and is great for edge devices with limited resources. You can build and run models easily, including GPT-2, and it supports CUDA, Android, and other hardware. This means you can use advanced AI models faster and cheaper on your existing devices.
https://github.com/ggml-org/ggml
GGML is a lightweight, efficient tensor library written in C that helps you run large machine learning models on everyday hardware like laptops, phones, and even Raspberry Pi. It supports integer quantization (reducing model size and speeding up processing), automatic differentiation, and works across many platforms without needing extra software. GGML uses zero memory allocation during runtime, which improves performance and is great for edge devices with limited resources. You can build and run models easily, including GPT-2, and it supports CUDA, Android, and other hardware. This means you can use advanced AI models faster and cheaper on your existing devices.
https://github.com/ggml-org/ggml
GitHub
GitHub - ggml-org/ggml: Tensor library for machine learning
Tensor library for machine learning. Contribute to ggml-org/ggml development by creating an account on GitHub.