Awesome GitHub RepositoriesMemory Optimization Strategies

Ollama is a cross-platform runtime for managing, serving, and executing large language models on local hardware. It functions as a model manager and orchestrator that allows for the downloading, updating, and organization of model weights and configurations to ensure private and offline inference. The system provides a local inference API and a RESTful interface for programmatic model lifecycle management and text generation. It utilizes a compiled C++ backend to handle tensor operations and memory management. To support various hardware configurations, the runtime employs dynamic GPU offloa

ComfyUI is a modular generative AI workflow orchestrator and node-based GUI for designing and executing complex diffusion model pipelines. It functions as both a visual interface for building generative logic graphs and a programmable backend API that exposes diffusion model operations for external integration. The system distinguishes itself through a graph-based execution model that supports differential workflow execution, re-running only modified nodes to reduce computation. It features dynamic model offloading to manage memory between system RAM and GPU VRAM and utilizes metadata-embedde

Ray is a distributed computing framework designed to scale Python and Java applications across clusters by abstracting task scheduling and resource management. It functions as a resource-aware execution engine that manages task dependencies, placement, and fault tolerance across networked compute nodes. At its core, the system provides a stateful actor model, allowing developers to define classes that run in dedicated processes to maintain and mutate internal state across remote method calls. The framework distinguishes itself through a robust cross-language interoperability layer, enabling f

Fairseq is a PyTorch toolkit for sequence-to-sequence modeling, specializing in neural machine translation, automatic speech recognition, and large-scale language model training. It provides a framework for processing and aligning diverse data sources, including text, audio, and video, to support tasks such as speech-to-text conversion and multimodal sequence learning. The project is distinguished by its distributed training capabilities, which utilize parameter sharding, mixed-precision training, and CPU offloading to handle models that exceed single-device memory. It also includes specializ

Backtrader is a Python framework designed for the development, backtesting, and live execution of algorithmic trading strategies. It provides a comprehensive environment for quantitative finance, allowing users to simulate trading logic against historical market data or connect directly to brokerage platforms for automated real-time trading. The project distinguishes itself through a unified event-driven architecture that treats backtesting and live trading with the same API. This consistency is supported by a flexible data-feed abstraction layer that normalizes diverse financial sources, ena

Niri is a Wayland compositor and tiling window manager designed for Linux systems. It functions as a display server that organizes application windows into a scrollable, column-based layout, providing a structured environment for managing graphical sessions, input routing, and hardware output. The project distinguishes itself through a declarative configuration engine that enables live-reloading of settings, allowing users to modify window rules, input bindings, and visual appearance without restarting the session. It features a physics-based animation system that uses spring-based curves to

Blender is a professional 3D creation suite designed for modeling, animation, rendering, and video editing. It functions as an open-source 3D engine that provides a comprehensive framework for procedural geometry, physics simulation, and high-quality visual output. The platform is built upon a foundational architecture that utilizes data-block-based memory management and a dependency-graph-based evaluation system to handle complex scene transformations and geometry updates. The software distinguishes itself through a highly modular, node-based procedural architecture that allows users to cons

This is a PyTorch implementation of a neural style transfer system. It functions as a convolutional neural network image stylizer and artistic style blender designed to combine the content of one image with the artistic style of another. The system supports blending multiple style sources and adjusting the relative weights between content and style reconstruction. It includes capabilities for preserving the original color palette of the content image and adjusting style scales to determine which artistic patterns are transferred. The pipeline enables high-resolution image processing by distr

Nodemailer is a comprehensive library for Node.js applications designed to handle the composition, signing, and transmission of email messages. It provides a robust framework for constructing MIME-compliant content, managing complex attachments, and routing messages through various delivery channels, including standard SMTP servers, local mail transfer agents, and cloud-based email services. The library distinguishes itself through a modular, plugin-based transport architecture that allows for custom delivery mechanisms and environment-specific configurations. It includes advanced features fo

Subconverter is a network utility designed to translate, merge, and filter proxy subscription configurations. It functions as a service that converts proxy links between various client-specific formats, ensuring compatibility across different applications and platforms. By providing a unified interface for managing diverse connection sources, the tool enables consistent network policy application and streamlined configuration management. The project distinguishes itself through an HTTP-based transformation interface that processes subscription data dynamically. It utilizes an in-memory pipeli

Swin-Transformer is a deep learning framework designed for training and deploying hierarchical vision transformer models. It serves as a research library and toolkit for computer vision tasks, providing the infrastructure to build models that replace standard convolution operations with sliding window self-attention mechanisms. By utilizing a multi-scale feature hierarchy, the framework enables the processing of visual data at varying resolutions and spatial scales. The project distinguishes itself through its implementation of shifted window partitioning, which facilitates global information

OneDev is a self-hosted, unified development platform that integrates Git repository hosting, issue tracking, and continuous integration and deployment (CI/CD) into a single system. It provides a comprehensive environment for managing the entire software lifecycle, allowing teams to coordinate code reviews, track development tasks, and automate build pipelines through a centralized interface. The platform distinguishes itself by offering browser-based, containerized development environments that allow developers to access and edit project files directly on the server. Its build system utilize

Swift is a toolkit for the full-parameter and parameter-efficient fine-tuning of large language and multimodal models. It functions as a multimodal model trainer for text, image, video, and audio data, and includes specialized tools for model compression and reinforcement learning from human feedback. The framework provides an alignment toolkit for optimizing model behavior using preference learning algorithms and reinforcement learning. It integrates parameter-efficient fine-tuning methods to adapt models with minimal memory and compute requirements, alongside utilities for reducing hardware

MNN is a high-performance inference engine and framework designed for on-device machine learning. It provides a comprehensive environment for executing, optimizing, and deploying neural network models directly on mobile and resource-constrained edge devices. The framework distinguishes itself through a robust model optimization toolkit that supports quantization, compression, and structural graph manipulation to minimize memory footprint and maximize execution speed. It features a modular architecture that abstracts hardware-specific backends, allowing models to run efficiently across diverse

Axolotl is a distributed training orchestrator and fine-tuning framework for large language models, multimodal systems, and quantized models. It provides a structured environment for specializing pre-trained models through full parameter updates or low-rank adaptation, as well as aligning model outputs with human expectations via preference tuning pipelines and reward modeling. The system distinguishes itself through a configuration-driven pipeline that manages preprocessing and training workflows via a single file for reproducibility. It implements high-throughput optimizations such as multi

This project is a quantized fine-tuning framework for large language models. It implements a low-rank adaptation library and a four-bit quantizer to reduce the GPU memory requirements needed to train large models. The framework utilizes four-bit quantization and low-rank adapters to enable model training on consumer-grade hardware. It further reduces the memory footprint through double quantization and a paged optimizer that offloads states to system RAM. The system supports distributed training across multiple GPUs to handle larger parameter scales and includes utilities for custom dataset

The Android NDK samples provide a comprehensive collection of code examples demonstrating how to integrate C and C++ native code into Android applications. This repository serves as a practical guide for developers utilizing the Android Native Development Kit to implement performance-critical application components that require direct hardware access and low-level system interaction. The project highlights the use of the Java Native Interface to bridge managed code with native modules, enabling cross-language function calls and efficient data exchange. It demonstrates how to manage native act

Petals is a decentralized framework and inference engine for running large language models across a peer-to-peer network. It enables the execution of models that exceed the memory of any single machine by splitting computations and model layers across a collaborative swarm of GPUs. The system functions as a collaborative compute network where participants share local GPU resources and host model weights. It supports distributed prompt-tuning to adapt massive models to specific tasks and allows for the establishment of private compute swarms to process sensitive data within restricted, trusted

InternVL is a vision-language model framework that fuses a visual encoder with a large language model to translate image features into textual tokens for reasoning. It provides a system for multimodal inference and dialogue, enabling the processing of images and text to answer questions or generate descriptions. The project is distinguished by its high-resolution image processing, which uses dynamic tiling to maintain detail for images up to 4K resolution, and its chain-of-thought visual reasoning for solving complex mathematical and spatial problems. It also supports temporal frame sampling

Personaplex is an LLM speech-to-speech framework and conversational AI persona engine designed for real-time voice interfaces. It provides a system for defining AI identities and vocal characteristics through a combination of text-based role prompts and audio reference files. The project features a real-time AI voice interface that supports full-duplex human-AI dialogue, enabling multiple parties to speak and listen simultaneously via bidirectional audio streaming. It includes a GPU-accelerated audio processor and a speech-to-speech pipeline to facilitate low-latency conversations. The frame