FastDeploy is an inference and deployment toolkit for large language models and visual language models based on PaddlePaddle. It provides production-ready deployment solutions with core acceleration technologies such as load-balanced PD disaggregation, unified KV cache transmission, OpenAI API server compatibility, comprehensive quantization format support, advanced acceleration techniques, and multi-hardware support. The toolkit supports various hardware platforms like NVIDIA GPUs, Kunlunxin XPUs, Iluvatar GPUs, Enflame GCUs, and Hygon DCUs, with plans for expanding support to Ascend NPU and MetaX GPU. FastDeploy aims to optimize resource utilization, throughput, and performance for inference and deployment tasks.

Embodied-AI-Guide is a comprehensive guide for beginners to understand Embodied AI, focusing on the path of entry and useful information in the field. It covers topics such as Reinforcement Learning, Imitation Learning, Large Language Model for Robotics, 3D Vision, Control, Benchmarks, and provides resources for building cognitive understanding. The repository aims to help newcomers quickly establish knowledge in the field of Embodied AI.

BiBi-Keyboard is an AI-based intelligent voice input method that aims to make voice input more natural and efficient. It provides features such as voice recognition with simple and intuitive operations, multiple ASR engine support, AI text post-processing, floating ball input for cross-input method usage, AI editing panel with rich editing tools, Material3 design for modern interface style, and support for multiple languages. Users can adjust keyboard height, test input directly in the settings page, view recognition word count statistics, receive vibration feedback, and check for updates automatically. The tool requires Android 10.0 or higher, microphone permission for voice recognition, optional overlay permission for the floating ball feature, and optional accessibility permission for automatic text insertion.

Daily-DeepLearning is a repository that covers various computer science topics such as data structures, operating systems, computer networks, Python programming, data science packages like numpy, pandas, matplotlib, machine learning theories, deep learning theories, NLP concepts, machine learning practical applications, deep learning practical applications, and big data technologies like Hadoop and Hive. It also includes coding exercises related to '剑指offer'. The repository provides detailed explanations and examples for each topic, making it a comprehensive resource for learning and practicing different aspects of computer science and data-related fields.

LogChat is an open-source and free AI chat client that supports various chat models and technologies such as ChatGPT, 讯飞星火, DeepSeek, LLM, TTS, STT, and Live2D. The tool provides a user-friendly interface designed using Qt Creator and can be used on Windows systems without any additional environment requirements. Users can interact with different AI models, perform voice synthesis and recognition, and customize Live2D character models. LogChat also offers features like language translation, AI platform integration, and menu items like screenshot editing, clock, and application launcher.

Blueking Lite is an AI First lightweight operation product with low deployment resource requirements, low usage costs, and progressive experience, providing essential tools for operation administrators.

ChatWiki is an open-source knowledge base AI question-answering system. It is built on large language models (LLM) and retrieval-augmented generation (RAG) technologies, providing out-of-the-box data processing, model invocation capabilities, and helping enterprises quickly build their own knowledge base AI question-answering systems. It offers exclusive AI question-answering system, easy integration of models, data preprocessing, simple user interface design, and adaptability to different business scenarios.

KCORES LLM Arena is a large model evaluation tool that focuses on real-world scenarios, using human scoring and benchmark testing to assess performance. It aims to provide an unbiased evaluation of large models in real-world applications. The tool includes programming ability tests and specific benchmarks like Mandelbrot Set, Mars Mission, Solar System, and Ball Bouncing Inside Spinning Heptagon. It supports various programming languages and emphasizes performance optimization, rendering, animations, physics simulations, and creative implementations.

Academic Forge is a collection of skills integrated for academic writing workflows. It provides a curated set of skills related to academic writing and research, allowing for precise skill calls, avoiding confusion between similar skills, maintaining focus on research workflows, and receiving timely updates from original authors. The forge integrates carefully selected skills covering various areas such as bioinformatics, clinical research, data analysis, scientific writing, laboratory automation, machine learning, databases, AI research, model architectures, fine-tuning, post-training, distributed training, optimization, inference, evaluation, agents, multimodal tasks, and machine learning paper writing. It is designed to streamline the academic writing and AI research processes by providing a cohesive and community-driven collection of skills.

LLM_book is a learning record and roadmap for programmers with a certain AI foundation to learn Large Language Models (LLM). It covers topics such as PyTorch basics, Transformer architecture, langchain basics, foundational concepts of large models, fine-tuning methods, RAG (Retrieval-Augmented Generation), and building intelligent agents using LLM. The repository provides learning materials, code implementations, and documentation to help users progress in understanding and implementing LLM technologies.

LabelQuick_V2.0 is a fast image annotation tool designed and developed by the AI Horizon team. This version has been optimized and improved based on the previous version. It provides an intuitive interface and powerful annotation and segmentation functions to efficiently complete dataset annotation work. The tool supports video object tracking annotation, quick annotation by clicking, and various video operations. It introduces the SAM2 model for accurate and efficient object detection in video frames, reducing manual intervention and improving annotation quality. The tool is designed for Windows systems and requires a minimum of 6GB of memory.

hongbomiao.com is a personal research and development (R&D) lab that facilitates the sharing of knowledge. The repository covers a wide range of topics including web development, mobile development, desktop applications, API servers, cloud native technologies, data processing, machine learning, computer vision, embedded systems, simulation, database management, data cleaning, data orchestration, testing, ops, authentication, authorization, security, system tools, reverse engineering, Ethereum, hardware, network, guidelines, design, bots, and more. It provides detailed information on various tools, frameworks, libraries, and platforms used in these domains.

Aice PS is a powerful web-based AI photo editor that utilizes Google aistudio's advanced capabilities to make professional image editing and creation simple and intuitive. Users can enhance images, apply creative filters, make professional adjustments, and even generate new images from scratch using simple text prompts. The tool combines various cutting-edge AI capabilities to provide a one-stop creative image and video solution, including AI image generation, intelligent editing, creative filters, professional adjustments, AI inspiration suggestions, intelligent synthesis, texture overlay, one-click cutout, time travel effects, BeatSync for music and image synchronization, NB prompt word library, basic editing toolkit, and more.

Agenta is an open-source LLM developer platform for prompt engineering, evaluation, human feedback, and deployment of complex LLM applications. It provides tools for prompt engineering and management, evaluation, human annotation, and deployment, all without imposing any restrictions on your choice of framework, library, or model. Agenta allows developers and product teams to collaborate in building production-grade LLM-powered applications in less time.

MaiMBot is an intelligent QQ group chat bot based on a large language model. It is developed using the nonebot2 framework, utilizes LLM for conversation abilities, MongoDB for data persistence, and NapCat for QQ protocol support. The bot features keyword-triggered proactive responses, dynamic prompt construction, support for images and message forwarding, typo generation, multiple replies, emotion-based emoji responses, daily schedule generation, user relationship management, knowledge base, and group impressions. Work-in-progress features include personality, group atmosphere, image handling, humor, meme functions, and Minecraft interactions. The tool is in active development with plans for GIF compatibility, mini-program link parsing, bug fixes, documentation improvements, and logic enhancements for emoji sending.

Agentica is a human-centric framework for building large language model agents. It provides functionalities for planning, memory management, tool usage, and supports features like reflection, planning and execution, RAG, multi-agent, multi-role, and workflow. The tool allows users to quickly code and orchestrate agents, customize prompts, and make API calls to various services. It supports API calls to OpenAI, Azure, Deepseek, Moonshot, Claude, Ollama, and Together. Agentica aims to simplify the process of building AI agents by providing a user-friendly interface and a range of functionalities for agent development.

AutoGPTQ is an easy-to-use LLM quantization package with user-friendly APIs, based on GPTQ algorithm (weight-only quantization). It provides a simple and efficient way to quantize large language models (LLMs) to reduce their size and computational cost while maintaining their performance. AutoGPTQ supports a wide range of LLM models, including GPT-2, GPT-J, OPT, and BLOOM. It also supports various evaluation tasks, such as language modeling, sequence classification, and text summarization. With AutoGPTQ, users can easily quantize their LLM models and deploy them on resource-constrained devices, such as mobile phones and embedded systems.

Qwen-TensorRT-LLM is a project developed for the NVIDIA TensorRT Hackathon 2023, focusing on accelerating inference for the Qwen-7B-Chat model using TRT-LLM. The project offers various functionalities such as FP16/BF16 support, INT8 and INT4 quantization options, Tensor Parallel for multi-GPU parallelism, web demo setup with gradio, Triton API deployment for maximum throughput/concurrency, fastapi integration for openai requests, CLI interaction, and langchain support. It supports models like qwen2, qwen, and qwen-vl for both base and chat models. The project also provides tutorials on Bilibili and blogs for adapting Qwen models in NVIDIA TensorRT-LLM, along with hardware requirements and quick start guides for different model types and quantization methods.

The stable-diffusion.cpp repository provides an implementation for inferring stable diffusion in pure C/C++. It offers features such as support for different versions of stable diffusion, lightweight and dependency-free implementation, various quantization support, memory-efficient CPU inference, GPU acceleration, and more. Users can download the built executable program or build it manually. The repository also includes instructions for downloading weights, building from scratch, using different acceleration methods, running the tool, converting weights, and utilizing various features like Flash Attention, ESRGAN upscaling, PhotoMaker support, and more. Additionally, it mentions future TODOs and provides information on memory requirements, bindings, UIs, contributors, and references.

LMOps is a research initiative focusing on fundamental research and technology for building AI products with foundation models, particularly enabling AI capabilities with Large Language Models (LLMs) and Generative AI models. The project explores various aspects such as prompt optimization, longer context handling, LLM alignment, acceleration of LLMs, LLM customization, and understanding in-context learning. It also includes tools like Promptist for automatic prompt optimization, Structured Prompting for efficient long-sequence prompts consumption, and X-Prompt for extensible prompts beyond natural language. Additionally, LLMA accelerators are developed to speed up LLM inference by referencing and copying text spans from documents. The project aims to advance technologies that facilitate prompting language models and enhance the performance of LLMs in various scenarios.

Awesome-Efficient-LLM is a curated list focusing on efficient large language models. It includes topics such as knowledge distillation, network pruning, quantization, inference acceleration, efficient MOE, efficient architecture of LLM, KV cache compression, text compression, low-rank decomposition, hardware/system, tuning, and survey. The repository provides a collection of papers and projects related to improving the efficiency of large language models through various techniques like sparsity, quantization, and compression.

The NVIDIA TensorRT Model Optimizer is a library designed to quantize and compress deep learning models for optimized inference on GPUs. It offers state-of-the-art model optimization techniques including quantization and sparsity to reduce inference costs for generative AI models. Users can easily stack different optimization techniques to produce quantized checkpoints from torch or ONNX models. The quantized checkpoints are ready for deployment in inference frameworks like TensorRT-LLM or TensorRT, with planned integrations for NVIDIA NeMo and Megatron-LM. The tool also supports 8-bit quantization with Stable Diffusion for enterprise users on NVIDIA NIM. Model Optimizer is available for free on NVIDIA PyPI, and this repository serves as a platform for sharing examples, GPU-optimized recipes, and collecting community feedback.

Bolts package provides a variety of components to extend PyTorch Lightning, such as callbacks & datasets, for applied research and production. Users can accelerate Lightning training with the Torch ORT Callback to optimize ONNX graph for faster training & inference. Additionally, users can introduce sparsity with the SparseMLCallback to accelerate inference by leveraging the DeepSparse engine. Specific research implementations are encouraged, with contributions that help train SSL models and integrate with Lightning Flash for state-of-the-art models in applied research.

ms-swift is an official framework provided by the ModelScope community for fine-tuning and deploying large language models and multi-modal large models. It supports training, inference, evaluation, quantization, and deployment of over 400 large models and 100+ multi-modal large models. The framework includes various training technologies and accelerates inference, evaluation, and deployment modules. It offers a Gradio-based Web-UI interface and best practices for easy application of large models. ms-swift supports a wide range of model types, dataset types, hardware support, lightweight training methods, distributed training techniques, quantization training, RLHF training, multi-modal training, interface training, plugin and extension support, inference acceleration engines, model evaluation, and model quantization.

Weave is a toolkit for developing Generative AI applications, built by Weights & Biases. With Weave, you can log and debug language model inputs, outputs, and traces; build rigorous, apples-to-apples evaluations for language model use cases; and organize all the information generated across the LLM workflow, from experimentation to evaluations to production. Weave aims to bring rigor, best-practices, and composability to the inherently experimental process of developing Generative AI software, without introducing cognitive overhead.

LLMStack is a no-code platform for building generative AI agents, workflows, and chatbots. It allows users to connect their own data, internal tools, and GPT-powered models without any coding experience. LLMStack can be deployed to the cloud or on-premise and can be accessed via HTTP API or triggered from Slack or Discord.

The VisionCraft API is a free API for using over 100 different AI models. From images to sound.

Kaito is an operator that automates the AI/ML inference model deployment in a Kubernetes cluster. It manages large model files using container images, avoids tuning deployment parameters to fit GPU hardware by providing preset configurations, auto-provisions GPU nodes based on model requirements, and hosts large model images in the public Microsoft Container Registry (MCR) if the license allows. Using Kaito, the workflow of onboarding large AI inference models in Kubernetes is largely simplified.

PyRIT is an open access automation framework designed to empower security professionals and ML engineers to red team foundation models and their applications. It automates AI Red Teaming tasks to allow operators to focus on more complicated and time-consuming tasks and can also identify security harms such as misuse (e.g., malware generation, jailbreaking), and privacy harms (e.g., identity theft). The goal is to allow researchers to have a baseline of how well their model and entire inference pipeline is doing against different harm categories and to be able to compare that baseline to future iterations of their model. This allows them to have empirical data on how well their model is doing today, and detect any degradation of performance based on future improvements.

Tabby is a self-hosted AI coding assistant, offering an open-source and on-premises alternative to GitHub Copilot. It boasts several key features: * Self-contained, with no need for a DBMS or cloud service. * OpenAPI interface, easy to integrate with existing infrastructure (e.g Cloud IDE). * Supports consumer-grade GPUs.

SPEAR (Simulator for Photorealistic Embodied AI Research) is a powerful tool for training embodied agents. It features 300 unique virtual indoor environments with 2,566 unique rooms and 17,234 unique objects that can be manipulated individually. Each environment is designed by a professional artist and features detailed geometry, photorealistic materials, and a unique floor plan and object layout. SPEAR is implemented as Unreal Engine assets and provides an OpenAI Gym interface for interacting with the environments via Python.

Magick is a groundbreaking visual AIDE (Artificial Intelligence Development Environment) for no-code data pipelines and multimodal agents. Magick can connect to other services and comes with nodes and templates well-suited for intelligent agents, chatbots, complex reasoning systems and realistic characters.