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.

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.

BitMat is a Python package designed to optimize matrix multiplication operations by utilizing custom kernels written in Triton. It leverages the principles outlined in the "1bit-LLM Era" paper, specifically utilizing packed int8 data to enhance computational efficiency and performance in deep learning and numerical computing tasks.

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.

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.

GenAI Factory is a collection of end-to-end blueprints to deploy generative AI infrastructures in Google Cloud Platform (GCP), following security best practices. It embraces Infrastructure as Code (IaC) best practices, implements infrastructure in Terraform, and follows the least-privilege principle. The tool is compatible with Cloud Foundation Fabric FAST project-factory and application templates, allowing users to deploy various AI applications and systems on GCP.

R1-searcher is a tool designed to incentivize the search capability in large reasoning models (LRMs) via reinforcement learning. It enables LRMs to invoke web search and obtain external information during the reasoning process by utilizing a two-stage outcome-supervision reinforcement learning approach. The tool does not require instruction fine-tuning for cold start and is compatible with existing Base LLMs or Chat LLMs. It includes training code, inference code, model checkpoints, and a detailed technical report.

EasyLM is a one-stop solution for pre-training, fine-tuning, evaluating, and serving large language models in JAX/Flax. It simplifies the process by leveraging JAX's pjit functionality to scale up training to multiple TPU/GPU accelerators. Built on top of Huggingface's transformers and datasets, EasyLM offers an easy-to-use and customizable codebase for training large language models without the complexity found in other frameworks. It supports sharding model weights and training data across multiple accelerators, enabling multi-TPU/GPU training on a single host or across multiple hosts on Google Cloud TPU Pods. EasyLM currently supports models like LLaMA, LLaMA 2, and LLaMA 3.

This project enables users to create story videos by inputting a story theme, utilizing a large language model to generate AI-generated images, story content, audio, and subtitles. The backend is built with Python and FastAPI, while the frontend utilizes React, Ant Design, and Vite.

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.

iLLM-TSC is a framework that integrates reinforcement learning and large language models for traffic signal control policy improvement. It refines RL decisions based on real-world contexts and provides reasonable actions when RL agents make erroneous decisions. The framework includes cases where the large language model provides explanations and recommendations for RL agent actions, such as prioritizing emergency vehicles at intersections. Users can install and run the framework locally to train RL models and evaluate the combined RL+LLM approach.

Aligner is a model-agnostic alignment tool designed to efficiently correct responses from large language models. It redistributes initial answers to align with human intentions, improving performance across various LLMs. The tool can be applied with minimal training, enhancing upstream models and reducing hallucination. Aligner's 'copy and correct' method preserves the base structure while enhancing responses. It achieves significant performance improvements in helpfulness, harmlessness, and honesty dimensions, with notable success in boosting Win Rates on evaluation leaderboards.

Floki is an open-source framework for researchers and developers to experiment with LLM-based autonomous agents. It provides tools to create, orchestrate, and manage agents while seamlessly connecting to LLM inference APIs. Built on Dapr, Floki leverages a unified programming model that simplifies microservices and supports both deterministic workflows and event-driven interactions. By bringing together these features, Floki provides a powerful way to explore agentic workflows and the components that enable multi-agent systems to collaborate and scale, all powered by Dapr.

HookPHP is an open-source project that provides a PHP extension for hooking into various aspects of PHP applications. It allows developers to easily extend and customize the behavior of their PHP applications by providing hooks at key points in the execution flow. With HookPHP, developers can efficiently add custom functionality, modify existing behavior, and enhance the overall performance of their PHP applications. The project is licensed under the MIT license, making it accessible for developers to use and contribute to.

CodeFuse-muAgent is a Multi-Agent framework designed to streamline Standard Operating Procedure (SOP) orchestration for agents. It integrates toolkits, code libraries, knowledge bases, and sandbox environments for rapid construction of complex Multi-Agent interactive applications. The framework enables efficient execution and handling of multi-layered and multi-dimensional tasks.

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.

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.

OlympicArena is a comprehensive benchmark designed to evaluate advanced AI capabilities across various disciplines. It aims to push AI towards superintelligence by tackling complex challenges in science and beyond. The repository provides detailed data for different disciplines, allows users to run inference and evaluation locally, and offers a submission platform for testing models on the test set. Additionally, it includes an annotation interface and encourages users to cite their paper if they find the code or dataset helpful.

Edgen is a local GenAI API server that serves as a drop-in replacement for OpenAI's API. It provides multi-endpoint support for chat completions and speech-to-text, is model agnostic, offers optimized inference, and features model caching. Built in Rust, Edgen is natively compiled for Windows, MacOS, and Linux, eliminating the need for Docker. It allows users to utilize GenAI locally on their devices for free and with data privacy. With features like session caching, GPU support, and support for various endpoints, Edgen offers a scalable, reliable, and cost-effective solution for running GenAI applications locally.

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.

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.

LLM-Viewer is a tool for visualizing Language and Learning Models (LLMs) and analyzing performance on different hardware platforms. It enables network-wise analysis, considering factors such as peak memory consumption and total inference time cost. With LLM-Viewer, users can gain valuable insights into LLM inference and performance optimization. The tool can be used in a web browser or as a command line interface (CLI) for easy configuration and visualization. The ongoing project aims to enhance features like showing tensor shapes, expanding hardware platform compatibility, and supporting more LLMs with manual model graph configuration.

ServerlessLLM is a fast, affordable, and easy-to-use library designed for multi-LLM serving, optimized for environments with limited GPU resources. It supports loading various leading LLM inference libraries, achieving fast load times, and reducing model switching overhead. The library facilitates easy deployment via Ray Cluster and Kubernetes, integrates with the OpenAI Query API, and is actively maintained by contributors.

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.

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.