Projects sharing features with AITemplate

AidLearning-Framework is an integrated development platform for building and deploying AI applications on ARM-based devices. It combines Android and Linux operating systems running simultaneously on a single device, providing a unified runtime environment for cross-system AI development. The platform includes hardware acceleration across CPU, GPU, and NPU, with a unified API that automatically selects the optimal compute backend for inference. The framework distinguishes itself by enabling Python-based AI projects to be packaged directly into Android APK files for installation on mobile devic

HIP is a C++ GPU kernel language and cross-platform runtime designed for writing portable high-performance compute applications. It provides a programming interface that allows a single source codebase to execute on both AMD and NVIDIA GPU architectures. The project functions as a compatibility layer that enables the conversion and migration of existing CUDA source code to run on AMD hardware. This is achieved through a syntax mapping that mirrors CUDA and a source-to-source translation process during compilation. The toolkit covers the broader surface of cross-platform GPGPU development, in

Porffor is an ahead-of-time compiler that converts JavaScript and TypeScript source code into native machine code or C binaries. It functions as a native binary generator and transpiler, producing standalone executable files that do not require a runtime or virtual machine. The project translates source code into C language files and WebAssembly binary formats. It includes a direct-to-binary pipeline for TypeScript, allowing for the generation of target executables without a separate transpilation step to JavaScript. The toolset also includes an interactive read-eval-print loop for real-time

BentoML is a machine learning model serving framework and GPU-accelerated inference server designed to package, deploy, and scale AI models as production-ready REST APIs. It functions as an AI model lifecycle manager and an inference graph orchestrator, enabling the chaining of multiple models and custom logic into complex pipelines for advanced task sequences. The framework distinguishes itself through a dynamic batching engine that optimizes GPU throughput and an artifact-based packaging system that bundles model weights and dependencies into immutable archives for consistent deployment. It

Apex is a high-performance toolkit for PyTorch designed to coordinate distributed training, execute fused GPU kernels, manage mixed precision, and implement optimized distributed optimizers. It provides specialized tools for scaling model training across multiple GPUs and nodes to increase processing speed and throughput. The library features high-performance implementations of Adam and LAMB optimizers to reduce synchronization overhead and memory bottlenecks. It utilizes fused CUDA kernels to combine neural network operations, reducing memory overhead and increasing execution speed. The too

PaddleX is a PaddlePaddle-based framework for building, deploying, and fine-tuning AI model pipelines, with pre-built support for computer vision, OCR, document analysis, and time series tasks. It offers a toolkit of ready-to-use pipelines for image classification, object detection, segmentation, and pose estimation, alongside an end-to-end OCR document analysis pipeline that extracts text, tables, formulas, and layout information. The platform also includes a dedicated time series forecasting pipeline for analyzing historical data to detect anomalies, classify patterns, and predict future val

Spark NLP is a toolkit for scalable text analysis and machine learning built on the Apache Spark distributed computing framework. It provides a multimodal machine learning framework and a distributed pipeline system for sequencing annotators to process large-scale linguistic data. The library includes a transformer text processor for generating contextual vector embeddings and a dedicated inference engine for managing large language models. The project distinguishes itself through its ability to process heterogeneous data types, including text, audio, and images, within a unified vision-langu

KServe is a Kubernetes-native platform for deploying and serving machine learning models as scalable inference services. It supports both generative AI models, including large language models, and traditional predictive models from frameworks such as TensorFlow, PyTorch, Scikit-Learn, XGBoost, and ONNX. The platform manages the full lifecycle of model deployments, including revision tracking, canary rollouts, A/B testing, and automatic rollbacks, and provides serverless scale-to-zero capabilities for cost-efficient resource management. KServe distinguishes itself through a standardized infere

FastDeploy is a high-performance deployment framework for large language models, vision models, and multimodal models. It provides the infrastructure to launch model services that process combined image, video, and text inputs, exposing these capabilities through a standardized, OpenAI-compatible API for chat and text completions. The project distinguishes itself through advanced inference pipeline engineering and GPU optimization. It employs speculative decoding, tensor parallelism, and a disaggregated execution model that separates prefill and decode phases across different hardware resourc

LARK is a development toolkit for training, fine-tuning, and deploying large language models and multimodal models based on PaddlePaddle. It functions as a comprehensive framework that includes an LLM training orchestrator, an inference server, and a multimodal model framework for processing text, image, and video inputs. The project features a retrieval-augmented generation system for building conversational applications that integrate web search and private knowledge bases. It provides specific capabilities for multimodal reasoning and complex logic, enabling the extraction of structured da

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

The PyTorch Tutorials repository is a collection of educational resources that provides step-by-step guidance on building, training, and deploying neural networks using the PyTorch framework. It covers the complete machine learning workflow, from data loading and model definition through optimization loops and model persistence, with dedicated guides for distributed training, model fine-tuning, and deployment. The tutorials offer practical demonstrations of adapting pre-trained models to new tasks through transfer learning, scaling training across multiple GPUs or machines using PyTorch's dis

AutoGluon is an automated machine learning framework and multimodal library designed to automate the end-to-end pipeline from data preprocessing to high-accuracy model training and validation. It functions as an automated model trainer for tabular, image, text, and time series data, as well as a tool for time series forecasting and foundation model finetuning. The project is distinguished by its ability to jointly process and fuse different data types, allowing for the construction of multimodal neural networks that integrate images, text, and structured tables. It supports zero-shot inferenc

This project is a comprehensive instructional resource and course for building neural networks using PyTorch. It covers the fundamental building blocks of deep learning, including tensor manipulation, automatic differentiation, and the construction of modular neural network components. The repository serves as a technical guide for several specialized domains. It provides implementation details for computer vision tasks such as image classification, object detection, and semantic segmentation, as well as natural language processing workflows involving transformers, recurrent networks, and gen

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

This project provides a comprehensive technical guide and framework for engineering large-scale machine learning systems. It covers the full lifecycle of model development, focusing on the infrastructure and computational principles required to build, train, and serve generative AI models across distributed GPU clusters. The repository distinguishes itself by offering deep-dive tutorials and implementation strategies for complex system challenges. It emphasizes high-performance architectural primitives, such as collective communication orchestration, distributed tensor sharding, and static gr

Streamer-Sales is a digital avatar video generator and large language model sales agent framework. It functions as a multimodal AI pipeline that synthesizes talking-head videos using text-to-speech and face animation to create virtual spokespeople. The system differentiates itself by combining retrieval-augmented generation with agentic web searching to ground product descriptions and sales scripts in factual data and real-time information. It further integrates a multimodal interaction workflow that coordinates automatic speech recognition and text-to-speech for real-time voice conversations

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

LMCache is a distributed key-value cache manager and tiering system designed to accelerate large language model inference. It functions as a tiered storage layer that offloads tensors from GPU memory to CPU RAM, local disks, or remote object stores, enabling the reuse of cached prefixes across different inference sessions and serving engines. The system differentiates itself through a disaggregated prefill-decode model, which separates prompt processing from token generation by transferring caches between distributed compute nodes. It utilizes peer-to-peer orchestration to share and retrieve

FlashMLA is an LLM attention kernel library and inference acceleration library providing a collection of high-performance CUDA kernels. It implements multi-head latent attention mechanisms designed to reduce memory overhead and increase throughput during the forward and backward passes of large language model inference. The library utilizes quantized cache attention kernels to improve computation efficiency across both sparse and dense token processing. It specifically optimizes the prefill and decoding phases of model inference through these latent attention implementations. The project cov

Lorax is a GPU-accelerated inference server and multi-adapter engine designed for serving large language models. It functions as a high-throughput system capable of deploying models via Kubernetes and managing the dynamic swapping of Low-Rank Adaptation adapters per request. The server distinguishes itself through multi-adapter dynamic batching, which allows requests using different adapter weights to be processed in a single GPU forward pass. It employs just-in-time adapter loading and weighted adapter merging to maximize throughput and enable multi-tasking without sacrificing performance.

Nebullvm is an AI inference accelerator, GPU resource orchestrator, and performance optimization library for large language models. It functions as an optimization layer designed to lower operational costs by aligning model execution with underlying hardware architectures. The system maximizes cluster efficiency through real-time dynamic partitioning and elastic quotas for shared hardware resources. It employs alignment methods and techniques to reduce the hardware and data requirements necessary for tuning large language models. The project covers broad capability areas including AI infrast

GPyTorch is a GPU-accelerated probabilistic framework and PyTorch library for implementing scalable Gaussian process models. It provides a system for Gaussian process modeling and uncertainty estimation, designed to perform efficient matrix operations on graphics hardware. The framework features a modular kernel system for constructing custom covariance functions and modeling complex data dependencies. It specifically integrates Gaussian processes with deep neural networks to create hybrid models for regression and classification. The system employs numerical linear algebra techniques, inclu

xformers is a collection of specialized toolsets for fused GPU operators, sparse attention mechanisms, modular transformer components, and performance benchmarking. It provides a library of optimized and interoperable building blocks used to construct and experiment with transformer architectures. The project features a fused CUDA operator library that combines common layers into single GPU operations to increase throughput. It includes a sparse attention framework and memory-efficient attention kernels that utilize tiling strategies and structured sparsity patterns to reduce computational ov

AlphaFold3 is a biomolecular structure prediction model and bioinformatics structural analysis tool. It uses a deep learning system to predict the three-dimensional shapes of proteins, DNA, RNA, and ligands. The system functions as a diffusion-based protein folding model that predicts the spatial coordinates of biomolecular atoms and interactions. It utilizes a GPU-accelerated inference pipeline to process genetic sequences and structural templates for molecular modeling. The project covers structural bioinformatics analysis and protein interaction modeling to determine the physical arrangem

Text Embeddings Inference is a high-performance inference server designed to host text embedding and sequence classification models as scalable API endpoints. It provides a vector embedding API to convert text into dense representations and a cross-encoder reranking server for scoring the relevance of document sequences against a query. The project features a GPU-accelerated inference engine that utilizes dynamic batching and specialized kernels to maximize throughput. It offers a high-performance binary interface via gRPC as an alternative to standard HTTP to reduce network latency and seria

Nunchaku is a 4-bit model quantization library and diffusion model inference engine designed to run large-scale neural networks on consumer GPUs. It functions as a GPU-accelerated optimizer that reduces VRAM usage and increases inference speed through weight compression and memory management. The project utilizes low-rank weight decomposition and SVD weight quantization to compress models to four-bit precision while maintaining visual fidelity. It employs kernel-level operator fusion to minimize data movement and hardware-aware precision mapping to adjust numerical precision based on the unde