Awesome GitHub RepositoriesInference Acceleration Techniques

llama.cpp is a high-performance C++ inference engine and runtime for executing large language models locally across various hardware architectures. It provides the core components for local model execution, including a dedicated model quantizer for compressing weights into the GGUF format and a system for generating text embeddings for semantic search. The project distinguishes itself through specialized memory and execution optimizations, such as block-wise weight quantization to reduce memory footprints and memory-mapped model loading. It supports structured text generation by using formal

Unsloth is a high-performance training and inference platform designed to optimize the lifecycle of large language and multimodal models. It provides a comprehensive engine for fine-tuning, executing, and managing models locally, with a focus on reducing memory consumption and increasing compute speed on consumer-grade hardware. The platform distinguishes itself through hand-optimized kernels and automated computational graph techniques that maximize hardware throughput. It supports advanced training methodologies, including reinforcement learning for reasoning and efficient adapter-based fin

Sglang is a high-performance inference engine and serving system designed for large language and multimodal models. It provides a programmable interface for orchestrating complex generation workflows, enabling developers to coordinate multi-turn dialogues, tool invocations, and reasoning chains through a domain-specific language. The platform is built to support production-scale deployments, offering an OpenAI-compatible API that allows for integration with existing application ecosystems. The system distinguishes itself through a disaggregated architecture that separates compute-intensive pr

This project is a comprehensive engineering framework and technical reference for managing, scaling, and optimizing distributed machine learning infrastructure. It provides a suite of methodologies and diagnostic tools designed to support large-scale model training and inference on high-performance computing clusters. The project distinguishes itself through a specialized diagnostic toolkit and infrastructure optimization suite that addresses the complexities of multi-node environments. It enables precise control over cluster resources, including hardware maintenance, network topology configu

This project is a comprehensive toolkit designed for the full lifecycle management of large language and multimodal models. It functions as a unified orchestrator that handles the entire development process, ranging from dataset preparation and supervised fine-tuning to advanced reinforcement learning alignment and production-ready inference deployment. The platform distinguishes itself through a specialized reinforcement learning library that supports complex optimization algorithms, including group relative policy optimization and leave-one-out techniques, to improve model instruction-follo

PaddleNLP is a development library and toolkit for training, fine-tuning, and deploying large and small language models using the PaddlePaddle framework. It provides a comprehensive suite for the entire natural language processing lifecycle, from model development to high-performance inference. The project features a standardized model zoo for loading and managing pre-trained models and tokenizers through a unified interface. It distinguishes itself with a specialized model compression framework that reduces memory footprints via weight precision conversion and lossless size optimization, alo

Nano-vllm is a high-performance inference engine designed for executing large language models locally. It functions as a specialized runtime that prioritizes accelerated token generation and efficient hardware utilization for text generation tasks. The project distinguishes itself through a comprehensive suite of optimization techniques, including a graph compilation engine that transforms neural network operations into pre-compiled execution plans. It also incorporates a tensor parallelism framework to distribute model weights across multiple hardware accelerators, effectively reducing memor

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

llama-cpp-python provides a Python interface for the llama.cpp library, enabling the execution of large language models with hardware acceleration. It functions as a GGUF model loader and a structured text generator capable of running inference servers and multimodal runtimes for processing both text and image inputs. The project distinguishes itself through a local inference server that exposes model capabilities via an OpenAI-compatible web API. It supports advanced execution techniques including speculative decoding, weight quantization, and layer-based GPU offloading to manage memory acro

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

MiniCPM is a collection of small language models designed for local, on-device deployment in resource-constrained environments. The project focuses on running dense Transformer models on consumer hardware, including GPUs, CPUs, and Apple Silicon, without requiring custom code forks. The project distinguishes itself through heavy optimization for edge hardware, utilizing quantized weight compression in GGUF and MLX formats to reduce memory overhead. It implements advanced inference techniques such as speculative sampling and radix-tree prefix caching to accelerate generation speed and throughp

BigDL es un framework de aceleración de PyTorch y motor de inferencia distribuida diseñado para grandes modelos de lenguaje. Proporciona un kit de herramientas para ejecutar modelos en hardware Intel, integrando herramientas de cuantización y librerías para el ajuste fino eficiente en parámetros. El proyecto se distingue por el uso de paralelismo de pipeline para distribuir cargas de trabajo de modelos a través de múltiples aceleradores de hardware. Utiliza cuantización de enteros de bajo bit y decodificación especulativa para reducir la huella de memoria y disminuir la latencia de generación de texto. El sistema cubre amplias capacidades en optimización de modelos, incluyendo compresión de pesos y carga de modelos cuantizados. También admite rutinas de entrenamiento aceleradas por hardware para adaptar modelos preentrenados a tareas específicas.

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

jetson-inference is a set of libraries and tools for executing optimized deep learning models on embedded GPU hardware. Its primary purpose is to enable real-time computer vision and AI inference at the edge with low latency and high throughput. The project distinguishes itself through high-performance streaming analytics and the ability to execute concurrent AI pipelines on auto-grade silicon. It provides specialized support for multi-sensor stream processing, utilizing zero-copy data transport to load camera frames directly into GPU memory. The codebase covers a broad surface of capabiliti

LMFlow is a comprehensive suite for large language model fine-tuning, context extension, multimodal processing, and inference execution. It provides a toolkit for updating model parameters through full tuning or memory-efficient adapter algorithms, alongside an inference engine for executing tuned models via command-line or web-based interfaces. The framework includes a dedicated alignment suite for supervised tuning and reward model training to refine model behavior. It features a context window extender to increase maximum input lengths and a multimodal framework for building chatbots that

GLM-130B is a pre-trained foundation model and bilingual large language model designed for natural language processing tasks in both English and Chinese. It functions as an autoregressive language model and text generator capable of producing long-form content and predicting missing phrases. The model utilizes an autoregressive blank-filling architecture and a bidirectional dense transformer to process text. This approach allows the system to transition between understanding context through masked language modeling and generating sequential text using specific mask tokens. The project covers

This project provides a Chinese large language model based on the LLaMA architecture. It is an instruction-tuned model optimized for natural language processing and multi-turn conversations in Chinese. The system includes a framework for parameter-efficient fine-tuning using low-rank adaptation and quantization to reduce memory requirements. It also implements retrieval augmented generation for local document question answering and supports long-context processing for sequences up to 64K tokens. The project covers a broad set of capabilities including supervised instruction tuning, reinforce

mistral.rs is an inference engine for large language models that runs locally and exposes models behind OpenAI and Anthropic-compatible APIs. It serves as a multi-model serving platform, capable of loading several models in a single server process with per-request routing and on-demand loading and unloading. The engine supports multimodal inference, processing text alongside images, video, audio, and speech inputs, and includes a quantized model deployment runtime that reduces memory use and speeds up inference on consumer hardware. The project distinguishes itself through an agentic tool exe

gpt-fast es un motor de inferencia de transformadores de PyTorch diseñado para la generación de texto de baja latencia. Funciona como una librería de inferencia distribuida en GPU, un ejecutor de modelos cuantizados y un framework de decodificación especulativa. El sistema utiliza un flujo de trabajo de decodificación especulativa donde un modelo borrador pequeño predice secuencias de tokens para su verificación por un modelo más grande para acelerar la generación. Soporta la ejecución de modelos cuantizados para reducir la huella de memoria e implementa paralelismo de tensores para dividir los cálculos a través de múltiples GPUs. El proyecto incluye un arnés de evaluación estandarizado para medir la precisión y el rendimiento de los modelos de transformadores. Gestiona la eficiencia de la inferencia mediante la gestión de caché de clave-valor y el uso de operaciones de tensores nativas de PyTorch.

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.