Best AI tools for< Partition Gpus >

Doctrine is an AI-powered application that allows users to add AI-powered Q&A features to their apps in minutes. It leverages knowledge from data or knowledge bases to answer user questions or embed AI features. With the ability to ingest content from various sources like websites, documents, and images, Doctrine simplifies the process of knowledge extraction and enables seamless integration of AI capabilities into applications.

ClearML Fractional GPU is a tool designed to optimize GPU resource utilization by allowing multiple containers to run on the same GPU with driver-level memory limitation and compute time-slicing. It supports CUDA 11.x & CUDA 12.x, preventing greedy processes from grabbing the entire GPU memory. The tool offers options like Dynamic GPU Slicing, Container-based Memory Limits, and Kubernetes-based Static MIG Slicing to enhance hardware utilization and workload performance for AI development.

This repository contains a collection of tools that can be used with vastai. The tools are free to use, modify and distribute. If you find this useful and wish to donate your welcome to send your donations to the following wallets. BTC 15qkQSYXP2BvpqJkbj2qsNFb6nd7FyVcou XMR 897VkA8sG6gh7yvrKrtvWningikPteojfSgGff3JAUs3cu7jxPDjhiAZRdcQSYPE2VGFVHAdirHqRZEpZsWyPiNK6XPQKAg RVN RSgWs9Co8nQeyPqQAAqHkHhc5ykXyoMDUp USDT(ETH ERC20) 0xa5955cf9fe7af53bcaa1d2404e2b17a1f28aac4f Paypal PayPal.Me/cryptolabsZA

This competition is organized by Javier Rando and Florian Tramèr from the ETH AI Center and SPY Lab at ETH Zurich. The goal of the competition is to create a method that can detect universal backdoors in aligned language models. A universal backdoor is a secret suffix that, when appended to any prompt, enables the model to answer harmful instructions. The competition provides a set of poisoned generation models, a reward model that measures how safe a completion is, and a dataset with prompts to run experiments. Participants are encouraged to use novel methods for red-teaming, automated approaches with low human oversight, and interpretability tools to find the trojans. The best submissions will be offered the chance to present their work at an event during the SaTML 2024 conference and may be invited to co-author a publication summarizing the competition results.

Awesome-LLM-Inference: A curated list of 📙Awesome LLM Inference Papers with Codes, check 📖Contents for more details. This repo is still updated frequently ~ 👨‍💻‍ Welcome to star ⭐️ or submit a PR to this repo!

Awesome LLM compression research papers and tools to accelerate LLM training and inference.

The TensorRT-LLM Backend is a Triton backend designed to serve TensorRT-LLM models with Triton Inference Server. It supports features like inflight batching, paged attention, and more. Users can access the backend through pre-built Docker containers or build it using scripts provided in the repository. The backend can be used to create models for tasks like tokenizing, inferencing, de-tokenizing, ensemble modeling, and more. Users can interact with the backend using provided client scripts and query the server for metrics related to request handling, memory usage, KV cache blocks, and more. Testing for the backend can be done following the instructions in the 'ci/README.md' file.

LLM_Web_search project gives local LLMs the ability to search the web by outputting a specific command. It uses regular expressions to extract search queries from model output and then utilizes duckduckgo-search to search the web. LangChain's Contextual compression and Okapi BM25 or SPLADE are used to extract relevant parts of web pages in search results. The extracted results are appended to the model's output.

TigerBot is a cutting-edge foundation for your very own LLM, providing a world-class large model for innovative Chinese-style contributions. It offers various upgrades and features, such as search mode enhancements, support for large context lengths, and the ability to play text-based games. TigerBot is suitable for prompt-based game engine development, interactive game design, and real-time feedback for playable games.

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.

This repository contains a comprehensive collection of 63 must-know Large Language Models (LLMs) interview questions. It covers topics such as the architecture of LLMs, transformer models, attention mechanisms, training processes, encoder-decoder frameworks, differences between LLMs and traditional statistical language models, handling context and long-term dependencies, transformers for parallelization, applications of LLMs, sentiment analysis, language translation, conversation AI, chatbots, and more. The readme provides detailed explanations, code examples, and insights into utilizing LLMs for various tasks.

Eagle is a family of Vision-Centric High-Resolution Multimodal LLMs that enhance multimodal LLM perception using a mix of vision encoders and various input resolutions. The model features a channel-concatenation-based fusion for vision experts with different architectures and knowledge, supporting up to over 1K input resolution. It excels in resolution-sensitive tasks like optical character recognition and document understanding.

Run your own AI cluster at home with everyday devices. Exo is experimental software that unifies existing devices into a powerful GPU, supporting wide model compatibility, dynamic model partitioning, automatic device discovery, ChatGPT-compatible API, and device equality. It does not use a master-worker architecture, allowing devices to connect peer-to-peer. Exo supports different partitioning strategies like ring memory weighted partitioning. Installation is recommended from source. Documentation includes example usage on multiple MacOS devices and information on inference engines and networking modules. Known issues include the iOS implementation lagging behind Python.

Easy, fast, and cheap pretrain, finetune, serving for everyone

NanoFlow is a throughput-oriented high-performance serving framework for Large Language Models (LLMs) that consistently delivers superior throughput compared to other frameworks by utilizing key techniques such as intra-device parallelism, asynchronous CPU scheduling, and SSD offloading. The framework proposes nano-batching to schedule compute-, memory-, and network-bound operations for simultaneous execution, leading to increased resource utilization. NanoFlow also adopts an asynchronous control flow to optimize CPU overhead and eagerly offloads KV-Cache to SSDs for multi-round conversations. The open-source codebase integrates state-of-the-art kernel libraries and provides necessary scripts for environment setup and experiment reproduction.

DISC-LawLLM is a legal domain large model that aims to provide professional, intelligent, and comprehensive **legal services** to users. It is developed and open-sourced by the Data Intelligence and Social Computing Lab (Fudan-DISC) at Fudan University.

The Universal Numbers Library is a header-only C++ template library designed for universal number arithmetic, offering alternatives to native integer and floating-point for mixed-precision algorithm development and optimization. It tailors arithmetic types to the application's precision and dynamic range, enabling improved application performance and energy efficiency. The library provides fast implementations of special IEEE-754 formats like quarter precision, half-precision, and quad precision, as well as vendor-specific extensions. It supports static and elastic integers, decimals, fixed-points, rationals, linear floats, tapered floats, logarithmic, interval, and adaptive-precision integers, rationals, and floats. The library is suitable for AI, DSP, HPC, and HFT algorithms.

aiokafka is an asyncio client for Kafka that provides high-level, asynchronous message producer and consumer functionalities. It allows users to interact with Kafka for sending and consuming messages in an efficient and scalable manner. The tool supports features like cluster layout retrieval, topic/partition leadership information, group coordination, and message consumption load balancing. Users can easily integrate aiokafka into their Python projects to work with Kafka seamlessly.

EDA-AI is a repository containing implementations of cutting-edge research papers in the field of chip design. It includes DeepPlace, PRNet, HubRouter, and PreRoutGNN models for tasks such as placement, routing, timing prediction, and global routing. Researchers and practitioners can leverage these implementations to explore advanced techniques in chip design.

OpenCat code running on BiBoard, a high-performance ESP32 quadruped robot development board. The board is mainly designed for developers and engineers working on multi-degree-of-freedom (MDOF) Multi-legged robots with up to 12 servos.

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.