kvcached is a new KV cache management system that supports on-demand KV cache allocation. It implements the concept of GPU virtual memory, allowing applications to reserve virtual address space without immediately committing physical memory. Physical memory is then automatically allocated and mapped as needed at runtime. This capability allows multiple LLMs to run concurrently on a single GPU or a group of GPUs (TP) and flexibly share the GPU memory, significantly improving GPU utilization and reducing memory fragmentation. kvcached is compatible with popular LLM serving engines, including SGLang and vLLM.

Shinkai apps unlock the full capabilities/automation of first-class LLM (AI) support in the web browser. It enables creating multiple agents, each connected to either local or 3rd-party LLMs (ex. OpenAI GPT), which have permissioned (meaning secure) access to act in every webpage you visit. There is a companion repo called Shinkai Node, that allows you to set up the node anywhere as the central unit of the Shinkai Network, handling tasks such as agent management, job processing, and secure communications.

ByteDance's Piano Transcription is a PyTorch implementation for transcribing piano recordings into MIDI files with pedals. This repository provides a simple GUI and packaging for Windows and Nix on Linux/macOS. It supports using GPU for inference and includes CLI usage. Users can upgrade the tool and report issues to the upstream project. The tool focuses on providing MIDI files, and any other improvements to transcription results should be directed to the original project.

RLHF Book is a work-in-progress textbook covering the fundamentals of Reinforcement Learning from Human Feedback (RLHF). It is built on the Pandoc book template and is meant for people with a basic ML and/or software background. The content for the book is licensed under the Creative Commons Non-Commercial Attribution License, CC BY-NC 4.0. The repository contains a simple template for building Pandoc documents, allowing users to compile markdown files into readable files such as PDF, EPUB, and HTML.

ControlLLM is a framework that empowers large language models to leverage multi-modal tools for solving complex real-world tasks. It addresses challenges like ambiguous user prompts, inaccurate tool selection, and inefficient tool scheduling by utilizing a task decomposer, a Thoughts-on-Graph paradigm, and an execution engine with a rich toolbox. The framework excels in tasks involving image, audio, and video processing, showcasing superior accuracy, efficiency, and versatility compared to existing methods.

Private ML SDK is a secure solution for running Large Language Models (LLMs) in Trusted Execution Environments (TEEs) using NVIDIA GPU TEE and Intel TDX technologies. It provides a tamper-proof data processing environment with secure execution, open-source builds, and nearly native speed performance. The system includes components like Secure Compute Environment, Remote Attestation, Secure Communication, and Key Management Service (KMS). Users can build TDX guest images, run Local KMS, and TDX guest images on TDX host machines with Nvidia GPUs. The SDK offers verifiable execution results and high performance for LLM workloads.

AIGNE DocSmith is a powerful AI-driven documentation generation tool that automates the creation of detailed, structured, and multi-language documentation directly from source code. It intelligently analyzes codebase to generate a comprehensive document structure, populates content with high-quality AI-powered generation, supports seamless translation into 12+ languages, integrates with AIGNE Hub for large language models, offers Discuss Kit publishing, automatically updates documentation with source code changes, and allows for individual document optimization.

DocETL is a tool for creating and executing data processing pipelines, especially suited for complex document processing tasks. It offers a low-code, declarative YAML interface to define LLM-powered operations on complex data. Ideal for maximizing correctness and output quality for semantic processing on a collection of data, representing complex tasks via map-reduce, maximizing LLM accuracy, handling long documents, and automating task retries based on validation criteria.

askrepo is a tool that reads the content of Git-managed text files in a specified directory, sends it to the Google Gemini API, and provides answers to questions based on a specified prompt. It acts as a question-answering tool for source code by using a Google AI model to analyze and provide answers based on the provided source code files. The tool leverages modules for file processing, interaction with the Google AI API, and orchestrating the entire process of extracting information from source code files.

Discord AI Chatbot is a versatile tool that seamlessly integrates into your Discord server, offering a wide range of capabilities to enhance your communication and engagement. With its advanced language model, the bot excels at imaginative generation, providing endless possibilities for creative expression. Additionally, it offers secure credential management, ensuring the privacy of your data. The bot's hybrid command system combines the best of slash and normal commands, providing flexibility and ease of use. It also features mention recognition, ensuring prompt responses whenever you mention it or use its name. The bot's message handling capabilities prevent confusion by recognizing when you're replying to others. You can customize the bot's behavior by selecting from a range of pre-existing personalities or creating your own. The bot's web access feature unlocks a new level of convenience, allowing you to interact with it from anywhere. With its open-source nature, you have the freedom to modify and adapt the bot to your specific needs.

llama.vim is a plugin that provides local LLM-assisted text completion for Vim users. It offers features such as auto-suggest on cursor movement, manual suggestion toggling, suggestion acceptance with Tab and Shift+Tab, control over text generation time, context configuration, ring context with chunks from open and edited files, and performance stats display. The plugin requires a llama.cpp server instance to be running and supports FIM-compatible models. It aims to be simple, lightweight, and provide high-quality and performant local FIM completions even on consumer-grade hardware.

xGitGuard is an AI-based system developed by Comcast Cybersecurity Research and Development team to detect secrets (e.g., API tokens, usernames, passwords) exposed on GitHub repositories. It uses advanced Natural Language Processing to detect secrets at scale and with appropriate velocity. The tool provides workflows for detecting credentials and keys/tokens in both enterprise and public GitHub accounts. Users can set up search patterns, configure API access, run detections with or without ML filters, and train ML models for improved detection accuracy. xGitGuard also supports custom keyword scans for targeted organizations or repositories. The tool is licensed under Apache 2.0.

Pebblo enables developers to safely load data and promote their Gen AI app to deployment without worrying about the organization’s compliance and security requirements. The project identifies semantic topics and entities found in the loaded data and summarizes them on the UI or a PDF report.

ChatIDE is an AI assistant that integrates with your IDE, allowing you to converse with OpenAI's ChatGPT or Anthropic's Claude within your development environment. It provides a seamless way to access AI-powered assistance while coding, enabling you to get real-time help, generate code snippets, debug errors, and brainstorm ideas without leaving your IDE.

This repository implements a speech-to-speech cascaded pipeline with consecutive parts including Voice Activity Detection (VAD), Speech to Text (STT), Language Model (LM), and Text to Speech (TTS). It aims to provide a fully open and modular approach by leveraging models available on the Transformers library via the Hugging Face hub. The code is designed for easy modification, with each component implemented as a class. Users can run the pipeline either on a server/client approach or locally, with detailed setup and usage instructions provided in the readme.

Aiogram bot template is a boilerplate for creating Telegram bots using Aiogram framework. It provides a solid foundation for building robust and scalable bots with a focus on code organization, database integration, and localization.

Arena-Hard-Auto-v0.1 is an automatic evaluation tool for instruction-tuned LLMs. It contains 500 challenging user queries. The tool prompts GPT-4-Turbo as a judge to compare models' responses against a baseline model (default: GPT-4-0314). Arena-Hard-Auto employs an automatic judge as a cheaper and faster approximator to human preference. It has the highest correlation and separability to Chatbot Arena among popular open-ended LLM benchmarks. Users can evaluate their models' performance on Chatbot Arena by using Arena-Hard-Auto.

The Modular Accelerated Xecution (MAX) platform is an integrated suite of AI libraries, tools, and technologies that unifies commonly fragmented AI deployment workflows. MAX accelerates time to market for the latest innovations by giving AI developers a single toolchain that unlocks full programmability, unparalleled performance, and seamless hardware portability.

AI Hub Project aims to continuously test and evaluate mainstream large language models, while accumulating and managing various effective model invocation prompts. It has integrated all mainstream large language models in China, including OpenAI GPT-4 Turbo, Baidu ERNIE-Bot-4, Tencent ChatPro, MiniMax abab5.5-chat, and more. The project plans to continuously track, integrate, and evaluate new models. Users can access the models through REST services or Java code integration. The project also provides a testing suite for translation, coding, and benchmark testing.

Long-Context-Attention (YunChang) is a unified sequence parallel approach that combines the strengths of DeepSpeed-Ulysses-Attention and Ring-Attention to provide a versatile and high-performance solution for long context LLM model training and inference. It addresses the limitations of both methods by offering no limitation on the number of heads, compatibility with advanced parallel strategies, and enhanced performance benchmarks. The tool is verified in Megatron-LM and offers best practices for 4D parallelism, making it suitable for various attention mechanisms and parallel computing advancements.

Marlin is a highly optimized FP16xINT4 matmul kernel designed for large language model (LLM) inference, offering close to ideal speedups up to batchsizes of 16-32 tokens. It is suitable for larger-scale serving, speculative decoding, and advanced multi-inference schemes like CoT-Majority. Marlin achieves optimal performance by utilizing various techniques and optimizations to fully leverage GPU resources, ensuring efficient computation and memory management.

This repository, MMC, focuses on advancing multimodal chart understanding through large-scale instruction tuning. It introduces a dataset supporting various tasks and chart types, a benchmark for evaluating reasoning capabilities over charts, and an assistant achieving state-of-the-art performance on chart QA benchmarks. The repository provides data for chart-text alignment, benchmarking, and instruction tuning, along with existing datasets used in experiments. Additionally, it offers a Gradio demo for the MMCA model.

Tiktoken is a high-performance implementation focused on token count operations. It provides various encodings like o200k_base, cl100k_base, r50k_base, p50k_base, and p50k_edit. Users can easily encode and decode text using the provided API. The repository also includes a benchmark console app for performance tracking. Contributions in the form of PRs are welcome.

ppl.llm.serving is a serving component for Large Language Models (LLMs) within the PPL.LLM system. It provides a server based on gRPC and supports inference for LLaMA. The repository includes instructions for prerequisites, quick start guide, model exporting, server setup, client usage, benchmarking, and offline inference. Users can refer to the LLaMA Guide for more details on using this serving component.

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.