llm_note

LLM notes repository contains detailed analysis on transformer models, language model compression, inference and deployment, high-performance computing, and system optimization methods. It includes discussions on various algorithms, frameworks, and performance analysis related to large language models and high-performance computing. The repository serves as a comprehensive resource for understanding and optimizing language models and computing systems.

PAIML MCP Agent Toolkit (PMAT) is a zero-configuration AI context generation system with extreme quality enforcement and Toyota Way standards. It allows users to analyze any codebase instantly through CLI, MCP, or HTTP interfaces. The toolkit provides features such as technical debt analysis, advanced monitoring, metrics aggregation, performance profiling, bottleneck detection, alert system, multi-format export, storage flexibility, and more. It also offers AI-powered intelligence for smart recommendations, polyglot analysis, repository showcase, and integration points. PMAT enforces quality standards like complexity ≤20, zero SATD comments, test coverage >80%, no lint warnings, and synchronized documentation with commits. The toolkit follows Toyota Way development principles for iterative improvement, direct AST traversal, automated quality gates, and zero SATD policy.

opcode is a powerful desktop application built with Tauri 2 that serves as a command center for interacting with Claude Code. It offers a visual GUI for managing Claude Code sessions, creating custom agents, tracking usage, and more. Users can navigate projects, create specialized AI agents, monitor usage analytics, manage MCP servers, create session checkpoints, edit CLAUDE.md files, and more. The tool bridges the gap between command-line tools and visual experiences, making AI-assisted development more intuitive and productive.

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.

Rime Wanxiang is a pinyin input method based on deep optimized lexicon and language model. It features a lexicon with tones, AI and large corpus filtering, and frequency addition to provide more accurate sentence output. The tool supports various input methods and customization options, aiming to enhance user experience through lexicon and transcription. Users can also refresh the lexicon with different types of auxiliary codes using the LMDG toolkit package. Wanxiang offers core features like tone-marked pinyin annotations, phrase composition, and word frequency, with customizable functionalities. The tool is designed to provide a seamless input experience based on lexicon and transcription.

ChatGPT WebUI is a user-friendly web graphical interface for various LLMs like ChatGPT, providing simplified features such as core ChatGPT conversation and document retrieval dialogues. It has been optimized for better RAG retrieval accuracy and supports various search engines. Users can deploy local language models easily and interact with different LLMs like GPT-4, Azure OpenAI, and more. The tool offers powerful functionalities like GPT4 API configuration, system prompt setup for role-playing, and basic conversation features. It also provides a history of conversations, customization options, and a seamless user experience with themes, dark mode, and PWA installation support.

AI Novel Writing Assistant is an intelligent productivity tool for novel creation based on AI + prompt words. It has been used by hundreds of studios and individual authors to quickly and batch generate novels. With AI technology to enhance writing efficiency and a comprehensive prompt word management feature, it achieves 20 times efficiency improvement in intelligent book disassembly, intelligent book title and synopsis generation, text polishing, and shift+L quick term insertion, making writing easier and more professional. It has been upgraded to v5.2. The tool supports mind map construction of outlines and chapters, AI self-optimization of novels, writing knowledge base management, shift+L quick term insertion in the text input field, support for any mainstream large models integration, custom skin color, prompt word import and export, support for large text memory, right-click polishing, expansion, and de-AI flavoring of outlines, chapters, and text, multiple sets of novel prompt word library management, and book disassembly function.

Shimmy is a 5.1MB single-binary local inference server providing OpenAI-compatible endpoints for GGUF models. It offers fast, reliable AI inference with sub-second responses, zero configuration, and automatic port management. Perfect for developers seeking privacy, cost-effectiveness, speed, and easy integration with popular tools like VSCode and Cursor. Shimmy is designed to be invisible infrastructure that simplifies local AI development and deployment.

evi-run is a powerful, production-ready multi-agent AI system built on Python using the OpenAI Agents SDK. It offers instant deployment, ultimate flexibility, built-in analytics, Telegram integration, and scalable architecture. The system features memory management, knowledge integration, task scheduling, multi-agent orchestration, custom agent creation, deep research, web intelligence, document processing, image generation, DEX analytics, and Solana token swap. It supports flexible usage modes like private, free, and pay mode, with upcoming features including NSFW mode, task scheduler, and automatic limit orders. The technology stack includes Python 3.11, OpenAI Agents SDK, Telegram Bot API, PostgreSQL, Redis, and Docker & Docker Compose for deployment.

MarkMap-OpenAi-ChatGpt is a Vue.js-based mind map generation tool that allows users to generate mind maps by entering titles or content. The application integrates the markmap-lib and markmap-view libraries, supports visualizing mind maps, and provides functions for zooming and adapting the map to the screen. Users can also export the generated mind map in PNG, SVG, JPEG, and other formats. This project is suitable for quickly organizing ideas, study notes, project planning, etc. By simply entering content, users can get an intuitive mind map that can be continuously expanded, downloaded, and shared.

ChatOllama is an open-source chatbot based on LLMs (Large Language Models). It supports a wide range of language models, including Ollama served models, OpenAI, Azure OpenAI, and Anthropic. ChatOllama supports multiple types of chat, including free chat with LLMs and chat with LLMs based on a knowledge base. Key features of ChatOllama include Ollama models management, knowledge bases management, chat, and commercial LLMs API keys management.

HexStrike AI is an advanced AI-powered penetration testing MCP framework with 150+ security tools and 12+ autonomous AI agents. It features a multi-agent architecture with intelligent decision-making, vulnerability intelligence, and modern visual engine. The platform allows for AI agent connection, intelligent analysis, autonomous execution, real-time adaptation, and advanced reporting. HexStrike AI offers a streamlined installation process, Docker container support, 250+ specialized AI agents/tools, native desktop client, advanced web automation, memory optimization, enhanced error handling, and bypassing limitations.

Fay is an open-source digital human framework that offers different versions for various purposes. The '带货完整版' is suitable for online and offline salespersons. The '助理完整版' serves as a human-machine interactive digital assistant that can also control devices upon command. The 'agent版' is designed to be an autonomous agent capable of making decisions and contacting its owner. The framework provides updates and improvements across its different versions, including features like emotion analysis integration, model optimizations, and compatibility enhancements. Users can access detailed documentation for each version through the provided links.

NodeTool is a platform designed for AI enthusiasts, developers, and creators, providing a visual interface to access a variety of AI tools and models. It simplifies access to advanced AI technologies, offering resources for content creation, data analysis, automation, and more. With features like a visual editor, seamless integration with leading AI platforms, model manager, and API integration, NodeTool caters to both newcomers and experienced users in the AI field.

LAYRA is the world's first visual-native AI automation engine that sees documents like a human, preserves layout and graphical elements, and executes arbitrarily complex workflows with full Python control. It empowers users to build next-generation intelligent systems with no limits or compromises. Built for Enterprise-Grade deployment, LAYRA features a modern frontend, high-performance backend, decoupled service architecture, visual-native multimodal document understanding, and a powerful workflow engine.

InterPilot is an AI-based assistant tool that captures audio from Windows input/output devices, transcribes it into text, and then calls the Large Language Model (LLM) API to provide answers. The project includes recording, transcription, and AI response modules, aiming to provide support for personal legitimate learning, work, and research. It may assist in scenarios like interviews, meetings, and learning, but it is strictly for learning and communication purposes only. The tool can hide its interface using third-party tools to prevent screen recording or screen sharing, but it does not have this feature built-in. Users bear the risk of using third-party tools independently.

LLM notes repository contains detailed analysis on transformer models, language model compression, inference and deployment, high-performance computing, and system optimization methods. It includes discussions on various algorithms, frameworks, and performance analysis related to large language models and high-performance computing. The repository serves as a comprehensive resource for understanding and optimizing language models and computing systems.

FlashInfer is a library for Language Languages Models that provides high-performance implementation of LLM GPU kernels such as FlashAttention, PageAttention and LoRA. FlashInfer focus on LLM serving and inference, and delivers state-the-art performance across diverse scenarios.

LangCorn is an API server that enables you to serve LangChain models and pipelines with ease, leveraging the power of FastAPI for a robust and efficient experience. It offers features such as easy deployment of LangChain models and pipelines, ready-to-use authentication functionality, high-performance FastAPI framework for serving requests, scalability and robustness for language processing applications, support for custom pipelines and processing, well-documented RESTful API endpoints, and asynchronous processing for faster response times.

Awesome-LLM is a curated list of resources related to large language models, focusing on papers, projects, frameworks, tools, tutorials, courses, opinions, and other useful resources in the field. It covers trending LLM projects, milestone papers, other papers, open LLM projects, LLM training frameworks, LLM evaluation frameworks, tools for deploying LLM, prompting libraries & tools, tutorials, courses, books, and opinions. The repository provides a comprehensive overview of the latest advancements and resources in the field of large language models.

Chuanhu Chat is a user-friendly web graphical interface that provides various additional features for ChatGPT and other language models. It supports GPT-4, file-based question answering, local deployment of language models, online search, agent assistant, and fine-tuning. The tool offers a range of functionalities including auto-solving questions, online searching with network support, knowledge base for quick reading, local deployment of language models, GPT 3.5 fine-tuning, and custom model integration. It also features system prompts for effective role-playing, basic conversation capabilities with options to regenerate or delete dialogues, conversation history management with auto-saving and search functionalities, and a visually appealing user experience with themes, dark mode, LaTeX rendering, and PWA application support.

DashInfer is a C++ runtime tool designed to deliver production-level implementations highly optimized for various hardware architectures, including x86 and ARMv9. It supports Continuous Batching and NUMA-Aware capabilities for CPU, and can fully utilize modern server-grade CPUs to host large language models (LLMs) up to 14B in size. With lightweight architecture, high precision, support for mainstream open-source LLMs, post-training quantization, optimized computation kernels, NUMA-aware design, and multi-language API interfaces, DashInfer provides a versatile solution for efficient inference tasks. It supports x86 CPUs with AVX2 instruction set and ARMv9 CPUs with SVE instruction set, along with various data types like FP32, BF16, and InstantQuant. DashInfer also offers single-NUMA and multi-NUMA architectures for model inference, with detailed performance tests and inference accuracy evaluations available. The tool is supported on mainstream Linux server operating systems and provides documentation and examples for easy integration and usage.

Awesome Mobile LLMs is a curated list of Large Language Models (LLMs) and related studies focused on mobile and embedded hardware. The repository includes information on various LLM models, deployment frameworks, benchmarking efforts, applications, multimodal LLMs, surveys on efficient LLMs, training LLMs on device, mobile-related use-cases, industry announcements, and related repositories. It aims to be a valuable resource for researchers, engineers, and practitioners interested in mobile LLMs.

llmaz is an easy, advanced inference platform for large language models on Kubernetes. It aims to provide a production-ready solution that integrates with state-of-the-art inference backends. The platform supports efficient model distribution, accelerator fungibility, SOTA inference, various model providers, multi-host support, and scaling efficiency. Users can quickly deploy LLM services with minimal configurations and benefit from a wide range of advanced inference backends. llmaz is designed to optimize cost and performance while supporting cutting-edge researches like Speculative Decoding or Splitwise on Kubernetes.

Awesome Mamba is a curated collection of groundbreaking research papers and articles on Mamba Architecture, a pioneering framework in deep learning known for its selective state spaces and efficiency in processing complex data structures. The repository offers a comprehensive exploration of Mamba architecture through categorized research papers covering various domains like visual recognition, speech processing, remote sensing, video processing, activity recognition, image enhancement, medical imaging, reinforcement learning, natural language processing, 3D recognition, multi-modal understanding, time series analysis, graph neural networks, point cloud analysis, and tabular data handling.

The 'unilm' repository is a collection of tools, models, and architectures for Foundation Models and General AI, focusing on tasks such as NLP, MT, Speech, Document AI, and Multimodal AI. It includes various pre-trained models, such as UniLM, InfoXLM, DeltaLM, MiniLM, AdaLM, BEiT, LayoutLM, WavLM, VALL-E, and more, designed for tasks like language understanding, generation, translation, vision, speech, and multimodal processing. The repository also features toolkits like s2s-ft for sequence-to-sequence fine-tuning and Aggressive Decoding for efficient sequence-to-sequence decoding. Additionally, it offers applications like TrOCR for OCR, LayoutReader for reading order detection, and XLM-T for multilingual NMT.

LLM App Stack, also known as Emerging Architectures for LLM Applications, is a comprehensive list of available tools, projects, and vendors at each layer of the LLM app stack. It covers various categories such as Data Pipelines, Embedding Models, Vector Databases, Playgrounds, Orchestrators, APIs/Plugins, LLM Caches, Logging/Monitoring/Eval, Validators, LLM APIs (proprietary and open source), App Hosting Platforms, Cloud Providers, and Opinionated Clouds. The repository aims to provide a detailed overview of tools and projects for building, deploying, and maintaining enterprise data solutions, AI models, and applications.

Awesome deep logic is a curated list of papers and resources focusing on integrating symbolic logic into deep neural networks. It includes surveys, tutorials, and research papers that explore the intersection of logic and deep learning. The repository aims to provide valuable insights and knowledge on how logic can be used to enhance reasoning, knowledge regularization, weak supervision, and explainability in neural networks.

Welcome to the ultimate hub for on-device Large Language Models (LLMs)! This repository is your go-to resource for all things related to LLMs designed for on-device deployment. Whether you're a seasoned researcher, an innovative developer, or an enthusiastic learner, this comprehensive collection of cutting-edge knowledge is your gateway to understanding, leveraging, and contributing to the exciting world of on-device LLMs.

DuoAttention is a framework designed to optimize long-context large language models (LLMs) by reducing memory and latency during inference without compromising their long-context abilities. It introduces a concept of Retrieval Heads and Streaming Heads to efficiently manage attention across tokens. By applying a full Key and Value (KV) cache to retrieval heads and a lightweight, constant-length KV cache to streaming heads, DuoAttention achieves significant reductions in memory usage and decoding time for LLMs. The framework uses an optimization-based algorithm with synthetic data to accurately identify retrieval heads, enabling efficient inference with minimal accuracy loss compared to full attention. DuoAttention also supports quantization techniques for further memory optimization, allowing for decoding of up to 3.3 million tokens on a single GPU.

LLM notes repository contains detailed analysis on transformer models, language model compression, inference and deployment, high-performance computing, and system optimization methods. It includes discussions on various algorithms, frameworks, and performance analysis related to large language models and high-performance computing. The repository serves as a comprehensive resource for understanding and optimizing language models and computing systems.

A curated list of high-quality papers on resource-efficient Large Language Models (LLMs) with a focus on various aspects such as architecture design, pre-training, fine-tuning, inference, system design, and evaluation metrics. The repository covers topics like efficient transformer architectures, non-transformer architectures, memory efficiency, data efficiency, model compression, dynamic acceleration, deployment optimization, support infrastructure, and other related systems. It also provides detailed information on computation metrics, memory metrics, energy metrics, financial cost metrics, network communication metrics, and other metrics relevant to resource-efficient LLMs. The repository includes benchmarks for evaluating the efficiency of NLP models and references for further reading.