Awesome GitHub RepositoriesMulti-GPU Distribution

Llama is a large language model runtime and inference engine designed to load and execute autoregressive transformer models. It enables the generation of natural language text completions from prompts using pretrained weights. The system features multi-GPU model parallelism, which distributes model weights and workloads across multiple graphics processors to support larger parameter counts. It also incorporates a content safety filter that uses classifiers to intercept and block unsafe inputs or outputs during the inference process. The project covers broad capabilities in distributed model

gpt-oss is an open-weight large language model and reasoning engine designed for complex reasoning and agentic workflows. It functions as an AI agent framework and model serving API, allowing for local deployment and the hosting of standardized interfaces to expose model completions and internal reasoning processes. The project distinguishes itself as a quantized inference engine, utilizing tensor parallelism and weight quantization to run high-parameter models on limited hardware. It features a reasoning model that employs chain-of-thought processing to solve multi-step logical tasks. The s

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

ChatGLM2-6B is an open-weight large language model designed for natural language conversations and text generation in both English and Chinese. It functions as a bilingual chat model capable of processing and maintaining coherence across text sequences up to 32K tokens. The model is optimized for local deployment through precision quantization, which reduces memory requirements to allow execution on consumer-grade hardware. It supports distributing model weights across multiple graphics cards to handle parameters that exceed the memory of a single device. The project covers capabilities for

ChatGLM2-6B is a bilingual chat large language model designed for natural conversation and text generation in both English and Chinese. It functions as a fine-tunable language model that supports updating weights via specialized scripts to adapt to specific datasets and tasks. The project serves as a quantized inference engine and multi-GPU model orchestrator, enabling the execution of large models on consumer-grade hardware. It is capable of processing long context sequences up to 32K tokens to maintain understanding across extended documents. The system covers capabilities for multilingual

ChatGLM3 is a comprehensive framework for deploying, fine-tuning, and serving large language models. It functions as a high-performance inference engine designed to support conversational AI, enabling developers to build interactive agents capable of multi-turn dialogue, autonomous code execution, and structured tool invocation. The project distinguishes itself through its focus on hardware-agnostic deployment and resource optimization. It supports distributed model parallelism across multiple graphics cards, paged key-value caching for concurrent request processing, and weight quantization t

CogVideo is a generative video framework that uses diffusion models and transformer-based architectures to synthesize high-resolution video clips. It functions as both a text-to-video and image-to-video generator, converting textual descriptions or static images into temporal visual sequences. The system integrates large language model capabilities to expand short user prompts into detailed descriptions for better visual alignment. It supports the animation of static images through latent seeding and provides the ability to extend the length of existing video sequences. The project includes

CogVideo is a video generation framework and large language model architecture designed for synthesizing high-resolution video clips from natural language descriptions and images. It functions as a text-to-video and image-to-video generator, while also providing a model for video captioning to analyze visual content into descriptive text summaries. The system supports animating static images into motion sequences and transforming series of images into video based on prompts. It includes capabilities for extending the length of generated video clips to create longer sequences of motion. The f

Open-Sora-Plan is a text-to-video framework and distributed video training system. It utilizes a diffusion transformer architecture and large language model components to transform written descriptions or image prompts into high-quality video sequences. The system features a distributed infrastructure designed for large-scale video training and inference. It employs sequence parallelism to split high-resolution or long-duration video samples across multiple GPUs and uses a sparse attention mechanism to increase processing speed. The project includes capabilities for both text-to-video and im

Este proyecto es una biblioteca y framework de inferencia de modelos de lenguaje de gran tamaño (LLM) diseñado para ejecutar modelos para generación de texto, resolución de problemas y asistencia en codificación. Incluye un framework multimodal para procesar entradas combinadas de imagen y texto, y una implementación de uso de herramientas que permite la ejecución de funciones externas basadas en el razonamiento del modelo. El sistema cuenta con un motor de inferencia de GPU distribuido que reparte las cargas de trabajo de modelos grandes a través de múltiples procesadores gráficos para aumentar la velocidad de procesamiento y cumplir con los requisitos de memoria. También proporciona despliegue de modelos en contenedores a través de imágenes preempaquetadas y dependencias para servir motores de inferencia en entornos aislados. La biblioteca cubre una gama de capacidades que incluyen análisis de entrada multimodal, integración de llamadas a funciones y codificación de relleno (fill-in-the-middle) para predecir segmentos de código faltantes. Además, admite chat interactivo con el modelo a través de una interfaz de línea de comandos para mantener sesiones conversacionales.

OpenVINO is an AI inference engine and model serving platform designed to execute optimized deep learning models across CPUs, GPUs, and NPUs through a unified API. It includes a model optimization toolkit for converting, quantizing, and compressing models from various frameworks, alongside a specialized generative AI runtime for large language models. The project distinguishes itself through a plugin-based hardware acceleration layer that maps neural network operations to vendor-specific drivers. It features advanced execution mechanisms such as continuous batching, speculative decoding, and

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

KoboldCPP is a local large language model inference engine and GGUF model runner designed to execute quantized models on personal hardware. It functions as a multimodal AI server and API gateway, providing OpenAI-compatible endpoints that allow third-party clients to interact with locally hosted models. The project distinguishes itself as an AI storytelling backend, featuring dedicated tools for long-form narrative management through persistent memory, world lore tracking, and character state management. It further extends its capabilities as a multimodal server capable of processing text, im

Intel XPU LLM Acceleration Library is a toolkit designed to accelerate large language model inference and finetuning on Intel CPUs, GPUs, and NPUs. It provides a distributed inference engine for scaling models across multiple accelerators, a multimodal model runtime for vision and speech tasks, and a low-bit model quantization tool for converting weights into INT4, FP8, and GGUF formats. The project features a parameter-efficient finetuning framework that enables model adaptation using QLoRA and DPO on Intel hardware. It distinguishes itself by providing specialized optimizations for Intel XP

PowerInfer is a high-performance local large language model inference engine and sparse inference framework. It provides a runtime for executing models on consumer-grade hardware, utilizing a GPU acceleration backend to optimize tensor operations for graphics processors. The system distinguishes itself through a sparse inference framework that increases generation speed by skipping computations based on activation sparsity in model weights. It includes a GGUF model converter for transforming weights and metadata into a unified binary format, as well as an OpenAI API compatible server for inte

pysheeet es una biblioteca de referencia técnica que proporciona una colección curada de fragmentos de código y patrones de implementación para el desarrollo avanzado en Python, integración de sistemas y computación de alto rendimiento. Sirve como una guía completa para implementar programación de red de bajo nivel, extensiones nativas en C y programación asíncrona y concurrente. El proyecto proporciona frameworks especializados para el desarrollo y despliegue de modelos de lenguaje de gran tamaño, incluyendo herramientas para inferencia distribuida en GPU y servicio de alto rendimiento. También incluye patrones detallados para la orquestación de clústeres de computación de alto rendimiento, cubriendo la asignación de recursos de GPU y la gestión de cargas de trabajo en múltiples nodos. La biblioteca cubre una amplia superficie de capacidades, incluyendo comunicación de red segura y criptografía, mapeo objeto-relacional y gestión de bases de datos, y la implementación de estructuras de datos y algoritmos complejos. También proporciona utilidades para la gestión de memoria, interoperabilidad nativa a través de interfaces de funciones externas e integración de sistemas operativos a nivel de sistema.

CogVLM is a multimodal large language model designed to integrate visual and textual data for reasoning about images and generating natural language. It functions as a visual question answering system that analyzes image content to provide detailed descriptions or answer specific questions. The project includes a visual grounding model capable of mapping text descriptions to precise bounding box coordinates within an image. It also features a vision-based automation agent that analyzes screen captures to generate execution plans and interaction coordinates for software interfaces. The system

Obliteratus is a weight ablation framework and refusal removal tool designed to identify and delete the internal representations responsible for content refusals in large language models without retraining. It functions as a circuit analysis suite that maps the geometric structure of model guardrails to isolate the specific layers and attention heads that enforce refusals. The project enables the removal of these behaviors through geometric projection, rank-1 adapter ablation for reversible modifications, and the application of steering vectors to alter behavior during inference. It includes

gpt-fast es un motor de inferencia de transformadores de PyTorch diseñado para la generación de texto utilizando una implementación de librería de tensores nativa. Proporciona un runtime para ejecutar modelos de lenguaje grandes sin necesidad de extensiones externas en C++. El proyecto implementa decodificación especulativa para acelerar la generación utilizando un modelo borrador pequeño para la predicción de tokens y un modelo más grande para la verificación. Optimiza aún más el rendimiento a través de una etapa de pre-llenado compilada y una librería de paralelismo de tensores multi-GPU que fragmenta capas lineales a través de múltiples unidades de procesamiento gráfico. La eficiencia de la memoria se gestiona a través de un runtime cuantizado que soporta pesos int8 e int4 y cuantización de tensores agrupados. El sistema también incluye herramientas para la parametrización de arquitectura, tokenización de texto y evaluación de precisión de modelos utilizando arneses estandarizados.

Warp is a Python framework that JIT-compiles Python functions into CUDA kernels for GPU-accelerated parallel computation, with built-in automatic differentiation and multi-framework array interoperability. At its core, it provides a GPU kernel compilation system that enables writing and executing custom GPU kernels directly from Python, while supporting automatic gradient computation through those kernels for integration with machine learning pipelines. The framework also includes tile-based cooperative computing, where thread blocks partition into tiles for shared-memory and tensor-core opera