#CPU

Explore the minimal Rust-based femtoGPT, adept in inference and training on both CPUs and GPUs via OpenCL—bypassing the need for massive CUDA installations. This open-source tool serves as an accessible research platform for CPU and GPU. Easily deployable with Rust toolchain, it invites AI enthusiasts to dive into hands-on learning while following developer insights from a planned book.

Llama_cpp-rs provides user-friendly and safe Rust bindings to the C++ library, llama.cpp, allowing for seamless execution of GGUF-based language models on CPUs, independent of machine learning expertise. Supporting diverse backends such as CUDA, Vulkan, Metal, and HIP/BLAS, the library is adaptable across various hardware environments. Users can efficiently load models and generate predictions with minimal coding efforts. It also delivers experimental functionalities like memory context size prediction. The project welcomes contributions while emphasizing a clean user experience and optimized performance through Cargo's release builds.

Discover a neural text-to-speech library for creating natural-sounding voices in Dart. This CPU-dependent, internet-free solution is ideal for developing realistic voice applications across platforms, ensuring smooth voice creation with minimal requirements. Learn about installation, dependencies, and examples to leverage modern voice synthesis.

This comprehensive guide details the process of how computers execute programs. Authored by experts in the field, it provides insights into CPU operations, syscalls, and multitasking, catering to readers without academic resources. Offering research-backed explanations from startup to execution, it is designed for those seeking a deeper understanding of computer mechanics. Begin your exploration with Chapter 1: The 'Basics'.

The project enhances the OpenPose algorithm for effective 2D multi-person pose estimation on CPU, maintaining accuracy. It employs a streamlined model to identify 18 keypoints per individual, achieving 40% AP on the COCO 2017 validation set. The repository includes essential code for training, validation, and conversion to OpenVINO format, with C++ and Python demo support, catering to developers seeking efficient pose estimation in limited-resource settings.

DeepSparse is an inference runtime that utilizes model sparsity to enhance neural network performance on CPUs. It works with SparseML for model pruning and quantization, improving inference speed and efficiency across various models such as LLMs, CNNs, and Transformers. The latest Sparse Fine-Tuning advancements enable up to 60% sparsity in models like MPT-7B without sacrificing accuracy, boosting performance significantly. It offers APIs including Engine, Pipeline, and Server for flexible integration and deployment, making it suitable for high-efficiency AI applications.