DistServe improves the performance of large language models serving by disaggregating the prefill and decoding computation. It allows setting parallelism configs and scheduling strategies for the two phases independently, handling KV-Cache communication and memory management automatically. Utilizes a high-performance C++ Transformer inference library SwiftTransformer with features like model/pipeline parallelism, FlashAttention, Continuous Batching, and PagedAttention. Supports GPT-2, OPT, and LLaMA2 models.

KAG is a logical reasoning and Q&A framework based on the OpenSPG engine and large language models. It is used to build logical reasoning and Q&A solutions for vertical domain knowledge bases. KAG supports logical reasoning, multi-hop fact Q&A, and integrates knowledge and chunk mutual indexing structure, conceptual semantic reasoning, schema-constrained knowledge construction, and logical form-guided hybrid reasoning and retrieval. The framework includes kg-builder for knowledge representation and kg-solver for logical symbol-guided hybrid solving and reasoning engine. KAG aims to enhance LLM service framework in professional domains by integrating logical and factual characteristics of KGs.

Sycamore is a conversational search and analytics platform for complex unstructured data, such as documents, presentations, transcripts, embedded tables, and internal knowledge repositories. It retrieves and synthesizes high-quality answers through bringing AI to data preparation, indexing, and retrieval. Sycamore makes it easy to prepare unstructured data for search and analytics, providing a toolkit for data cleaning, information extraction, enrichment, summarization, and generation of vector embeddings that encapsulate the semantics of data. Sycamore uses your choice of generative AI models to make these operations simple and effective, and it enables quick experimentation and iteration. Additionally, Sycamore uses OpenSearch for indexing, enabling hybrid (vector + keyword) search, retrieval-augmented generation (RAG) pipelining, filtering, analytical functions, conversational memory, and other features to improve information retrieval.

The AI Fairness 360 toolkit is an open-source library designed to detect and mitigate bias in machine learning models. It provides a comprehensive set of metrics, explanations, and algorithms for bias mitigation in various domains such as finance, healthcare, and education. The toolkit supports multiple bias mitigation algorithms and fairness metrics, and is available in both Python and R. Users can leverage the toolkit to ensure fairness in AI applications and contribute to its development for extensibility.

Sarathi-Serve is the official OSDI'24 artifact submission for paper #444, focusing on 'Taming Throughput-Latency Tradeoff in LLM Inference'. It is a research prototype built on top of CUDA 12.1, designed to optimize throughput-latency tradeoff in Large Language Models (LLM) inference. The tool provides a Python environment for users to install and reproduce results from the associated experiments. Users can refer to specific folders for individual figures and are encouraged to cite the paper if they use the tool in their work.

Aphrodite is the official backend engine for PygmalionAI, serving as the inference endpoint for the website. It allows serving Hugging Face-compatible models with fast speeds. Features include continuous batching, efficient K/V management, optimized CUDA kernels, quantization support, distributed inference, and 8-bit KV Cache. The engine requires Linux OS and Python 3.8 to 3.12, with CUDA >= 11 for build requirements. It supports various GPUs, CPUs, TPUs, and Inferentia. Users can limit GPU memory utilization and access full commands via CLI.

Collective Mind (CM) is a collection of portable, extensible, technology-agnostic and ready-to-use automation recipes with a human-friendly interface (aka CM scripts) to unify and automate all the manual steps required to compose, run, benchmark and optimize complex ML/AI applications on any platform with any software and hardware: see online catalog and source code. CM scripts require Python 3.7+ with minimal dependencies and are continuously extended by the community and MLCommons members to run natively on Ubuntu, MacOS, Windows, RHEL, Debian, Amazon Linux and any other operating system, in a cloud or inside automatically generated containers while keeping backward compatibility - please don't hesitate to report encountered issues here and contact us via public Discord Server to help this collaborative engineering effort! CM scripts were originally developed based on the following requirements from the MLCommons members to help them automatically compose and optimize complex MLPerf benchmarks, applications and systems across diverse and continuously changing models, data sets, software and hardware from Nvidia, Intel, AMD, Google, Qualcomm, Amazon and other vendors: * must work out of the box with the default options and without the need to edit some paths, environment variables and configuration files; * must be non-intrusive, easy to debug and must reuse existing user scripts and automation tools (such as cmake, make, ML workflows, python poetry and containers) rather than substituting them; * must have a very simple and human-friendly command line with a Python API and minimal dependencies; * must require minimal or zero learning curve by using plain Python, native scripts, environment variables and simple JSON/YAML descriptions instead of inventing new workflow languages; * must have the same interface to run all automations natively, in a cloud or inside containers. CM scripts were successfully validated by MLCommons to modularize MLPerf inference benchmarks and help the community automate more than 95% of all performance and power submissions in the v3.1 round across more than 120 system configurations (models, frameworks, hardware) while reducing development and maintenance costs.

ReaLHF is a distributed system designed for efficient RLHF training with Large Language Models (LLMs). It introduces a novel approach called parameter reallocation to dynamically redistribute LLM parameters across the cluster, optimizing allocations and parallelism for each computation workload. ReaL minimizes redundant communication while maximizing GPU utilization, achieving significantly higher Proximal Policy Optimization (PPO) training throughput compared to other systems. It supports large-scale training with various parallelism strategies and enables memory-efficient training with parameter and optimizer offloading. The system seamlessly integrates with HuggingFace checkpoints and inference frameworks, allowing for easy launching of local or distributed experiments. ReaLHF offers flexibility through versatile configuration customization and supports various RLHF algorithms, including DPO, PPO, RAFT, and more, while allowing the addition of custom algorithms for high efficiency.

Aphrodite is an inference engine optimized for serving HuggingFace-compatible models at scale. It leverages vLLM's Paged Attention technology to deliver high-performance model inference for multiple concurrent users. The engine supports continuous batching, efficient key/value management, optimized CUDA kernels, quantization support, distributed inference, and modern samplers. It can be easily installed and launched, with Docker support for deployment. Aphrodite requires Linux or Windows OS, Python 3.8 to 3.12, and CUDA >= 11. It is designed to utilize 90% of GPU VRAM but offers options to limit memory usage. Contributors are welcome to enhance the engine.

AgentDojo is a dynamic environment designed to evaluate prompt injection attacks and defenses for large language models (LLM) agents. It provides a benchmark script to run different suites and tasks with specified LLM models, defenses, and attacks. The tool is under active development, and users can inspect the results through dedicated documentation pages and the Invariant Benchmark Registry.

FedLLM-Bench is a realistic benchmark for the Federated Learning of Large Language Models community. It includes datasets for federated instruction tuning and preference alignment tasks, exhibiting diversities in language, quality, quantity, instruction, sequence length, embedding, and preference. The repository provides training scripts and code for open-ended evaluation, aiming to facilitate research and development in federated learning of large language models.

EasyDist is an automated parallelization system and infrastructure designed for multiple ecosystems. It offers usability by making parallelizing training or inference code effortless with just a single line of change. It ensures ecological compatibility by serving as a centralized source of truth for SPMD rules at the operator-level for various machine learning frameworks. EasyDist decouples auto-parallel algorithms from specific frameworks and IRs, allowing for the development and benchmarking of different auto-parallel algorithms in a flexible manner. The architecture includes MetaOp, MetaIR, and the ShardCombine Algorithm for SPMD sharding rules without manual annotations.

NeMo Framework is a generative AI framework built for researchers and pytorch developers working on large language models (LLMs), multimodal models (MM), automatic speech recognition (ASR), and text-to-speech synthesis (TTS). The primary objective of NeMo is to provide a scalable framework for researchers and developers from industry and academia to more easily implement and design new generative AI models by being able to leverage existing code and pretrained models.

SuperKnowa is a fast framework to build Enterprise RAG (Retriever Augmented Generation) Pipelines at Scale, powered by watsonx. It accelerates Enterprise Generative AI applications to get prod-ready solutions quickly on private data. The framework provides pluggable components for tackling various Generative AI use cases using Large Language Models (LLMs), allowing users to assemble building blocks to address challenges in AI-driven text generation. SuperKnowa is battle-tested from 1M to 200M private knowledge base & scaled to billions of retriever tokens.

AITemplate (AIT) is a Python framework that transforms deep neural networks into CUDA (NVIDIA GPU) / HIP (AMD GPU) C++ code for lightning-fast inference serving. It offers high performance close to roofline fp16 TensorCore (NVIDIA GPU) / MatrixCore (AMD GPU) performance on major models. AITemplate is unified, open, and flexible, supporting a comprehensive range of fusions for both GPU platforms. It provides excellent backward capability, horizontal fusion, vertical fusion, memory fusion, and works with or without PyTorch. FX2AIT is a tool that converts PyTorch models into AIT for fast inference serving, offering easy conversion and expanded support for models with unsupported operators.

aiexe is a cutting-edge command-line interface (CLI) and graphical user interface (GUI) tool that integrates powerful AI capabilities directly into your terminal or desktop. It is designed for developers, tech enthusiasts, and anyone interested in AI-powered automation. aiexe provides an easy-to-use yet robust platform for executing complex tasks with just a few commands. Users can harness the power of various AI models from OpenAI, Anthropic, Ollama, Gemini, and GROQ to boost productivity and enhance decision-making processes.

DistServe improves the performance of large language models serving by disaggregating the prefill and decoding computation. It allows setting parallelism configs and scheduling strategies for the two phases independently, handling KV-Cache communication and memory management automatically. Utilizes a high-performance C++ Transformer inference library SwiftTransformer with features like model/pipeline parallelism, FlashAttention, Continuous Batching, and PagedAttention. Supports GPT-2, OPT, and LLaMA2 models.

Motorhead is a memory and information retrieval server for LLMs. It provides three simple APIs to assist with memory handling in chat applications using LLMs. The first API, GET /sessions/:id/memory, returns messages up to a maximum window size. The second API, POST /sessions/:id/memory, allows you to send an array of messages to Motorhead for storage. The third API, DELETE /sessions/:id/memory, deletes the session's message list. Motorhead also features incremental summarization, where it processes half of the maximum window size of messages and summarizes them when the maximum is reached. Additionally, it supports searching by text query using vector search. Motorhead is configurable through environment variables, including the maximum window size, whether to enable long-term memory, the model used for incremental summarization, the server port, your OpenAI API key, and the Redis URL.

MemGPT is a system that intelligently manages different memory tiers in LLMs in order to effectively provide extended context within the LLM's limited context window. For example, MemGPT knows when to push critical information to a vector database and when to retrieve it later in the chat, enabling perpetual conversations. MemGPT can be used to create perpetual chatbots with self-editing memory, chat with your data by talking to your local files or SQL database, and more.

Polyfire is an all-in-one managed backend for AI apps that allows users to build AI applications directly from the frontend, eliminating the need for a separate backend. It simplifies the process by providing most backend services in just a few lines of code. With Polyfire, users can easily create chatbots, transcribe audio files, generate simple text, manage long-term memory, and generate images. The tool also offers starter guides and tutorials to help users get started quickly and efficiently.

GPTSwarm is a graph-based framework for LLM-based agents that enables the creation of LLM-based agents from graphs and facilitates the customized and automatic self-organization of agent swarms with self-improvement capabilities. The library includes components for domain-specific operations, graph-related functions, LLM backend selection, memory management, and optimization algorithms to enhance agent performance and swarm efficiency. Users can quickly run predefined swarms or utilize tools like the file analyzer. GPTSwarm supports local LM inference via LM Studio, allowing users to run with a local LLM model. The framework has been accepted by ICML2024 and offers advanced features for experimentation and customization.

Since the emergence of chatGPT in 2022, the acceleration of Large Language Model has become increasingly important. Here is a list of papers on LLMs inference and serving.

Bosquet is a tool designed for LLMOps in large language model-based applications. It simplifies building AI applications by managing LLM and tool services, integrating with Selmer templating library for prompt templating, enabling prompt chaining and composition with Pathom graph processing, defining agents and tools for external API interactions, handling LLM memory, and providing features like call response caching. The tool aims to streamline the development process for AI applications that require complex prompt templates, memory management, and interaction with external systems.

LangChain-Udemy-Course is a comprehensive course directory focusing on LangChain, a framework for generative AI applications. The course covers various aspects such as OpenAI API usage, prompt templates, Chains exploration, callback functions, memory techniques, RAG implementation, autonomous agents, hybrid search, LangSmith utilization, microservice architecture, and LangChain Expression Language. Learners gain theoretical knowledge and practical insights to understand and apply LangChain effectively in generative AI scenarios.

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.