Open-source alternatives to Paddle Lite

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

Burn is a deep learning framework designed for building, training, and deploying neural networks using a modular architecture. As a machine learning library built in Rust, it provides a backend-agnostic computational engine that enables the execution of models across diverse hardware, including central processors, graphics processors, and web runtimes. The framework distinguishes itself through a highly portable design that allows developers to maintain a single workflow for both training and inference across heterogeneous environments. It incorporates advanced optimization techniques such as

This repository serves as a comprehensive collection of reference implementations for the PyTorch machine learning library. It provides practical examples for building, training, and deploying deep learning models, functioning as a toolkit for developers to explore neural network architectures and training workflows. The project distinguishes itself by offering concrete demonstrations of complex machine learning operations, ranging from computer vision tasks like object detection and depth estimation to the training of large-scale transformer models. These examples illustrate how to implement

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

ipex-llm is an acceleration library and inference engine designed to optimize the execution and finetuning of large language models on Intel GPUs and NPUs. It provides a HuggingFace compatible model backend and a dedicated quantization toolkit for converting model weights into low-bit precision formats. The project facilitates distributed inference by splitting large model workloads across multiple accelerators using pipeline and tensor parallelism. It enables the deployment of models on Intel Arc, Flex, and Max GPUs to increase throughput and reduce latency. The library covers a broad range

LitGPT is a training and deployment framework for large language models, providing a suite of tools for pretraining, finetuning, quantizing, evaluating, and serving models within a production environment. It includes a dedicated training pipeline for adapting pretrained models to specific tasks, a quantization tool for reducing weight precision, and an inference server for hosting models via web interfaces. The framework supports high-performance model development through custom architecture implementation and the use of predefined recipes to standardize pretraining and finetuning. It enables

Metaseq is a transformer sequence modeling toolkit designed for training, fine-tuning, and deploying sequence-to-sequence models using open pre-trained weights. It provides a comprehensive framework for large language model training, including dedicated tools for sequence dataset processing and a standalone inference server for generating text via API requests. The project features specialized utilities for model quantization to reduce parameter precision to eight bits, which lowers memory usage and increases inference speed. It also includes a checkpoint conversion pipeline to transform mode

This project provides a foundational framework and reference implementation for executing causal language modeling and multimodal reasoning on local systems. It includes a set of core components for managing model assets, a fine-tuning framework, and structural definitions required to instantiate transformer-based architectures. The system is distinguished by its ability to process combined text and image inputs through multimodal transformer models for visual reasoning and document analysis. It also supports the deployment of quantized models, reducing memory footprints through low-precision

AISystem is a comprehensive AI full-stack infrastructure project covering the entire pipeline from AI chip architecture to high-level training frameworks. It encompasses the development of AI compiler frameworks, inference engines, and distributed training orchestrators designed to coordinate workloads across a heterogeneous compute stack of CPUs, GPUs, and NPUs. The project focuses on the deep integration of software and hardware, employing software-hardware co-design to align tensor layouts with physical memory structures. It provides specialized capabilities for accelerating Transformer mo

This project is a cross-platform machine learning inference engine designed to execute pre-trained models across diverse operating systems and hardware environments. It functions as a standardized execution framework that manages the entire lifecycle of model inference, from loading and graph optimization to hardware-accelerated execution and generative sequence management. The runtime distinguishes itself through a highly modular architecture that decouples model logic from hardware-specific kernels. By utilizing an execution provider abstraction, it enables developers to offload computation

This project is a comprehensive computer vision library for the PyTorch ecosystem, providing a standardized collection of neural network architectures, datasets, and high-performance transformation utilities. It serves as a foundational framework for building, training, and deploying deep learning models, offering a centralized model registry that allows developers to instantiate architectures with pre-trained weights for tasks such as image classification, object detection, and semantic segmentation. The library distinguishes itself through its modular approach to data and compute management

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

MiniCPM-V is a multimodal large language model and vision-language system designed for complex visual and linguistic understanding. It functions as an on-device AI model, providing the capacity to process text, images, and video as a compact neural network. The project is specifically developed as an edge AI framework, utilizing quantization and weight sharding to run on memory-constrained mobile chipsets. This allows for the deployment of multimodal intelligence directly on mobile operating systems for local inference. Its capabilities cover multimodal content analysis of high-resolution 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

llm-compressor is a quantization toolkit and post-training library designed to reduce the memory footprint and size of large language models. It provides a framework for compressing models using weight and activation quantization to enable more efficient deployment. The project distinguishes itself through a distributed quantization framework that utilizes data-parallel processing and disk-based weight offloading to handle massive model checkpoints that exceed available system memory. It includes specialized compressors for diverse architectures, including Mixture-of-Experts, Vision-Language,

bitsandbytes is a quantization library for large language models that reduces memory footprints using k-bit quantization. It provides a framework for 4-bit low-rank adaptation, tools for 8-bit model compression, and memory-efficient optimizer extensions for PyTorch. The project enables the training of large models on limited hardware through 4-bit quantization and low-rank adaptation weights. It also facilitates faster inference by compressing models to 8-bit precision using vector-wise quantization. The library covers a range of memory optimization capabilities, including optimizer memory r

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

This project provides a suite of lightweight face detection models designed for high-speed inference on edge computing devices. It centers on a compact neural network architecture that enables human face detection within environments characterized by limited compute resources and power constraints. The system features quantized face detectors available in multiple formats to ensure compatibility across diverse hardware architectures. It includes utilities for model export and quantization, allowing trained weights to be converted into standardized formats for hardware-agnostic deployment. Th

Torchtune is a PyTorch-native library for fine-tuning, aligning, and quantizing large language models. It provides a configurable training pipeline orchestrated through YAML recipes, with CLI overrides and component swapping, distributed training via FSDP2, memory optimizations, and parameter-efficient fine-tuning methods like LoRA, DoRA, and QLoRA. The library distinguishes itself through its YAML-driven configuration system that defines all training parameters and instantiates components from config files, with full CLI override capability for any field or component at launch time. It suppo

This project is a vision language model framework and vision-to-text pipeline designed for deploying and optimizing models that process both images and text. It provides an on-device inference engine and a vision language model framework to run quantized models locally on mobile and desktop hardware accelerators. The framework features a model quantization toolkit to reduce weight precision for lower memory footprints and increased execution speed on specialized silicon. It also includes an efficient vision encoder utilizing a hybrid encoding system to compress image tokens, which reduces pro

CTranslate2 is a C++ inference engine and runtime for Transformer models, designed to execute models on both CPU and GPU with optimizations for speed and memory efficiency. It functions as a model format converter, quantization tool, and REST API server, enabling deployment of neural machine translation, automatic speech recognition, and text generation models. The engine distinguishes itself through a suite of runtime optimizations including layer fusion, weight-matrix quantization, batch-by-length grouping, and a caching allocator that reuses GPU memory. It supports tensor-parallel model di

This project is a library and command-line interface for local large language model inference. It enables the generation of text completions and chat responses from various model architectures. The project provides tools for weight quantization to reduce memory footprints and incorporates hardware acceleration through GPU offloading to increase computation speed. It also includes utilities for model evaluation by measuring perplexity on specific datasets. Capabilities cover the full inference lifecycle, including binary model loading, template-based prompt structuring, and session persistenc

BigDL is a PyTorch acceleration framework and distributed inference engine designed for large language models. It provides a toolkit for running models on Intel hardware, integrating quantization tools and libraries for parameter-efficient fine-tuning. The project distinguishes itself through the use of pipeline parallelism to distribute model workloads across multiple hardware accelerators. It utilizes low-bit integer quantization and speculative decoding to reduce memory footprints and decrease text generation latency. The system covers broad capabilities in model optimization, including w

Jetson Containers is a container management system that builds and runs GPU-accelerated Docker images for machine learning workloads on ARM64 edge hardware. It functions as a CUDA container orchestrator, automatically detecting the host's CUDA toolkit version and GPU capabilities to ensure container compatibility at runtime, while selecting the correct container image by matching the host's JetPack or L4T version at launch time. The project delivers pre-configured containers for executing quantized large language models and retrieval-augmented generation pipelines optimized for edge devices,

alpaca.cpp is a high-performance local inference engine implemented in C++ for executing instruction-tuned large language models. It serves as a quantized model runtime designed to load and run model tensors on local hardware with minimal dependencies, removing the requirement for a full Python environment. The project focuses on on-device text generation and the deployment of private AI chatbots. It utilizes model weight quantization to reduce memory requirements and increase inference speed on consumer-grade devices. The system covers hardware-optimized model execution through thread-pool

whisper.cpp is a C++ implementation of the Whisper speech-to-text model, serving as a lightweight machine learning inference engine and quantized runtime. It provides high-performance automatic speech recognition and real-time audio transcription without requiring a Python environment. The project utilizes model quantization to reduce memory usage and increase inference speed on local hardware. It incorporates hardware acceleration to optimize processing speed across different processors. The system covers audio processing capabilities including voice activity detection, speaker diarization,

Neutts is a neural text-to-speech engine designed for real-time streaming output on edge devices such as phones and laptops. It supports voice cloning from short audio references, enabling zero-shot reproduction of a target speaker's voice, and can be fine-tuned or retrained from scratch for custom voices and styles. The system distinguishes itself through a decoder-only architecture that halves memory and accelerates generation on constrained hardware, combined with quantized model inference for reduced memory footprint. Its streaming decoder loop interleaves synthesis with playback, deliver