Search Results for "memory"

...The command downloads the base.en model converted to custom ggml format and runs the inference on all .wav samples in the folder samples. whisper.cpp supports integer quantization of the Whisper ggml models. Quantized models require less memory and disk space and depending on the hardware can be processed more efficiently.

VulkanSceneGraph (VSG), is a modern, cross-platform, high-performance scene graph library built upon Vulkan graphics/compute API. The software is written in C++17 and follows the CppCoreGuidelines and FOSS Best Practices. The source code is published under the MIT License, with the exception of vulkan.h, used for Vulkan extensions, which is under Apache License 2.0. This repository contains C++ headers and source and CMake build scripts to build the libvsg library. Additional support...

...Generally, major machine learning frameworks and libraries are focused on minimizing inference latency and/or maximizing throughput, all of which at the cost of RAM usage. So I decided to write a super small and hackable inference library specifically focused on minimizing memory consumption: OnnxStream. OnnxStream is based on the idea of decoupling the inference engine from the component responsible for providing the model weights, which is a class derived from WeightsProvider. A WeightsProvider specialization can implement any type of loading, caching, and prefetching of the model parameters.

...It includes a framework for 3D volumetric grids (for mapping), a localization algorithm based on scan matching, and two SLAM solutions (an Online SLAM and a Particle Filter SLAM). The main feature is efficiency. Low computational effort and low memory usage whenever possible. The minimum viable computer to run our localization and SLAM solutions is a Raspberry Pi 3 Model B+. We provide a fast scan-matching approach to mobile robot localization supported by a continuous likelihood field. It can be used to provide accurate localization for robots equipped with a laser and a not-so-good odometry. ...

...It was originally developed as an open-source alternative to i2c and 1-Wire but during development, its scope and features have been extended to cover use cases where IP is generally applied. PJON has been engineered to have a variable footprint (4.2-8.2 kB program memory) and overhead (5-35 bytes per packet) depending on its configuration.