Best AI tools for< Run With Multiple Gpus >

Stablematic is a web-based platform that allows users to run Stable Diffusion and other machine learning models without the need for local setup or hardware limitations. It provides a user-friendly interface, pre-installed plugins, and dedicated GPU resources for a seamless and efficient workflow. Users can generate images and videos from text prompts, merge multiple models, train custom models, and access a range of pre-trained models, including Dreambooth and CivitAi models. Stablematic also offers API access for developers and dedicated support for users to explore and utilize the capabilities of Stable Diffusion and other machine learning models.

Vidura is a prompt management system integrated with multiple AI systems, designed to enhance the Generative AI experience. Users can compose, organize, share, and export AI prompts efficiently. The platform offers features like categorizing prompts, built-in templates, prompt history audit, dynamic prompting, and community sharing. Vidura aims to simplify the process of generating text and image responses with AI, making it accessible and user-friendly for a wider audience.

Social Places is a leading franchise marketing agency that provides a suite of tools to help businesses with multiple locations manage their online presence. The platform includes tools for managing listings, reputation, social media, ads, and bookings. Social Places also offers a conversational AI chatbot and a custom feedback form builder.

Luminal is a powerful AI copilot that helps users clean, transform, and analyze spreadsheets 10x faster. It offers fast and efficient data analysis capabilities, enabling users to perform complex operations and run AI-enabled tasks using natural language. Luminal is designed to simplify data processing tasks, saving users time and effort. With support for multiple languages and secure data hosting, Luminal is a versatile tool suitable for both personal and professional use.

LiveReacting is a professional live streaming software that enables users to create branded and interactive live stream shows, interviews, and more. It offers features such as pre-recorded videos, interactive games, polls, countdowns, and customizable templates. Ideal for social media managers, digital agencies, brands, and creators, LiveReacting helps engage audiences and increase followers through its innovative tools and functionalities.

ChatGPT for Outlook is an AI tool that integrates the power of ChatGPT into Microsoft Outlook, allowing users to run ChatGPT on emails to generate summaries, highlights, and important information. Users can create custom prompts, process entire emails or specific parts, manage multiple configurations, and improve email efficiency. Blueberry Consultants, the developer, offers custom versions for businesses and teams, enabling users to resell the tool with unique prompts. The tool enhances productivity and information management within Outlook, leveraging AI technology for email processing and organization.

Replit is a software creation platform that provides an integrated development environment (IDE), artificial intelligence (AI) assistance, and deployment services. It allows users to build, test, and deploy software projects directly from their browser, without the need for local setup or configuration. Replit offers real-time collaboration, code generation, debugging, and autocompletion features powered by AI. It supports multiple programming languages and frameworks, making it suitable for a wide range of development projects.

GPT Prompt Tuner is an AI tool designed to enhance ChatGPT prompts by generating variations and running conversations in parallel. It aims to streamline the process of prompt engineering, offering users the ability to customize prompts, receive AI-generated variations, and engage in multiple ChatGPT conversations simultaneously. The tool provides flexible subscription plans, including options for monthly, yearly, and enterprise usage. With a focus on improving prompt quality and efficiency, GPT Prompt Tuner empowers users to optimize their interactions with ChatGPT.

ConversAI is an AI-powered chat assistant designed to enhance online communication. It uses natural language processing and machine learning to understand and respond to messages in a conversational manner. With ConversAI, users can quickly generate personalized responses, summarize long messages, detect the tone of conversations, communicate in multiple languages, and even add GIFs to their replies. It integrates seamlessly with various messaging platforms and tools, making it easy to use and efficient. ConversAI helps users save time, improve their communication skills, and have more engaging conversations online.

Botonomous is an AI-powered platform that helps businesses automate their workflows. With Botonomous, you can create advanced automations for any domain, check your flows for potential errors before running them, run multiple nodes concurrently without waiting for the completion of the previous step, create complex, non-linear flows with no-code, and design human interactions to participate in your automations. Botonomous also offers a variety of other features, such as webhooks, scheduled triggers, secure secret management, and a developer community.

Edyt AI is an AI-powered content optimization tool designed to help users create SEO-optimized content effortlessly. With the ability to generate articles in seconds and run multiple AI iterations on content, Edyt AI streamlines the content creation process. Users can improve existing blogs with just a few clicks, add external and internal links, and optimize content for better rankings. The tool ensures content quality by analyzing thousands of articles and words, making it a valuable asset for content creators and marketers.

Raman Labs is an AI tool that offers dedicated modules for computer vision-based tasks, allowing users to integrate machine learning functionality into their existing applications with just 2 lines of code. The tool provides real-time performance, simplicity, robustness to large scale and resolution variations, versatility, and adaptability to different computing power levels. It supports various platforms, hardware, and language integrations, with more coming soon. Raman Labs prioritizes user privacy by storing only email and hashed passwords, and all payment-related information is handled by a PCI DSS compliant service. The tool is licensed for personal use and can be run on multiple personal devices.

ONNX Runtime is a production-grade AI engine designed to accelerate machine learning training and inferencing in various technology stacks. It supports multiple languages and platforms, optimizing performance for CPU, GPU, and NPU hardware. ONNX Runtime powers AI in Microsoft products and is widely used in cloud, edge, web, and mobile applications. It also enables large model training and on-device training, offering state-of-the-art models for tasks like image synthesis and text generation.

Windows Central is a website that provides news, reviews, and help on Windows 10, Windows 11, Xbox, and more. It covers a wide range of topics, including hardware, software, gaming, and accessories. The website also has a forum where users can ask questions and discuss topics related to Windows and Xbox.

LM Studio is an AI tool designed for discovering, downloading, and running local LLMs (Large Language Models). Users can run LLMs on their laptops offline, use models through an in-app Chat UI or a local server, download compatible model files from HuggingFace repositories, and discover new LLMs. The tool ensures privacy by not collecting data or monitoring user actions, making it suitable for personal and business use. LM Studio supports various models like ggml Llama, MPT, and StarCoder on Hugging Face, with minimum hardware/software requirements specified for different platforms.

Breeze.ai is an AI-powered platform that helps businesses create professional-looking product photography, social media content, and marketing collateral in a fraction of the time and cost of traditional methods. With Breeze.ai, businesses can generate thousands of custom content in days, not weeks, at 50% of the monthly cost of traditional methods. Breeze.ai is trusted by companies globally and has helped thousands of users create content with AI.

TraqCheck is an AI-powered agent for background checks that offers simple, fast, and reliable verifications verified by human experts. It brings inhuman speed and transparency to the verification process, enabling quick hiring decisions at scale. TraqCheck supports various types of checks, including ID, criminal, education, employment history, and more. The platform helps in managing hiring smartly by tracking progress, running analytics, and generating reports on-the-fly. With powerful features like HRMS integration, AI-powered insights, API integration, and more, TraqCheck enhances the hiring process and boosts efficiency and scalability.

SAO (Search Ads Optimization) is an AI optimization platform for Apple Search Ads that automates keyword bid management to help scale revenue, increase installs, and reduce cost per acquisition. It offers in-depth analytics, data visualization, and advanced ASO tools for optimizing and automating Apple Search Ads campaigns. Trusted by app companies worldwide, SAO uses AI automation to run 24/7 with real-time data, allowing users to focus on strategic tasks while the platform manages campaigns efficiently.

Sacred is a tool to configure, organize, log and reproduce computational experiments. It is designed to introduce only minimal overhead, while encouraging modularity and configurability of experiments. The ability to conveniently make experiments configurable is at the heart of Sacred. If the parameters of an experiment are exposed in this way, it will help you to: keep track of all the parameters of your experiment easily run your experiment for different settings save configurations for individual runs in files or a database reproduce your results In Sacred we achieve this through the following main mechanisms: Config Scopes are functions with a @ex.config decorator, that turn all local variables into configuration entries. This helps to set up your configuration really easily. Those entries can then be used in captured functions via dependency injection. That way the system takes care of passing parameters around for you, which makes using your config values really easy. The command-line interface can be used to change the parameters, which makes it really easy to run your experiment with modified parameters. Observers log every information about your experiment and the configuration you used, and saves them for example to a Database. This helps to keep track of all your experiments. Automatic seeding helps controlling the randomness in your experiments, such that they stay reproducible.

Dora is a no-code 3D animated website design platform that allows users to create stunning 3D and animated visuals without writing a single line of code. With Dora, designers, freelancers, and creative professionals can focus on what they do best: designing. The platform is tailored for professionals who prioritize design aesthetics without wanting to dive deep into the backend. Dora offers a variety of features, including a drag-and-connect constraint layout system, advanced animation capabilities, and pixel-perfect usability. With Dora, users can create responsive 3D and animated websites that translate seamlessly across devices.

AI-Horde-Worker is a repository containing the original reference implementation for a worker that turns your graphics card(s) into a worker for the AI Horde. It allows users to generate or alchemize images for others. The repository provides instructions for setting up the worker on Windows and Linux, updating the worker code, running with multiple GPUs, and stopping the worker. Users can configure the worker using a WebUI to connect to the horde with their username and API key. The repository also includes information on model usage and running the Docker container with specified environment variables.

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.

InfLLM is a training-free memory-based method that unveils the intrinsic ability of LLMs to process streaming long sequences. It stores distant contexts into additional memory units and employs an efficient mechanism to lookup token-relevant units for attention computation. Thereby, InfLLM allows LLMs to efficiently process long sequences while maintaining the ability to capture long-distance dependencies. Without any training, InfLLM enables LLMs pre-trained on sequences of a few thousand tokens to achieve superior performance than competitive baselines continually training these LLMs on long sequences. Even when the sequence length is scaled to 1, 024K, InfLLM still effectively captures long-distance dependencies.

Qwen is a series of large language models developed by Alibaba DAMO Academy. It outperforms the baseline models of similar model sizes on a series of benchmark datasets, e.g., MMLU, C-Eval, GSM8K, MATH, HumanEval, MBPP, BBH, etc., which evaluate the models’ capabilities on natural language understanding, mathematic problem solving, coding, etc. Qwen models outperform the baseline models of similar model sizes on a series of benchmark datasets, e.g., MMLU, C-Eval, GSM8K, MATH, HumanEval, MBPP, BBH, etc., which evaluate the models’ capabilities on natural language understanding, mathematic problem solving, coding, etc. Qwen-72B achieves better performance than LLaMA2-70B on all tasks and outperforms GPT-3.5 on 7 out of 10 tasks.

This repository provides the latest implementation for the AI Horde Worker, allowing users to utilize their graphics card(s) to generate, post-process, or analyze images for others. It offers a platform where users can create images and earn 'kudos' in return, granting priority for their own image generations. The repository includes important details for setup, recommendations for system configurations, instructions for installation on Windows and Linux, basic usage guidelines, and information on updating the AI Horde Worker. Users can also run the worker with multiple GPUs and receive notifications for updates through Discord. Additionally, the repository contains models that are licensed under the CreativeML OpenRAIL License.

Meta Lingua is a minimal and fast LLM training and inference library designed for research. It uses easy-to-modify PyTorch components to experiment with new architectures, losses, and data. The codebase enables end-to-end training, inference, and evaluation, providing tools for speed and stability analysis. The repository contains essential components in the 'lingua' folder and scripts that combine these components in the 'apps' folder. Researchers can modify the provided templates to suit their experiments easily. Meta Lingua aims to lower the barrier to entry for LLM research by offering a lightweight and focused codebase.

CogVideo is an open-source repository that provides pretrained text-to-video models for generating videos based on input text. It includes models like CogVideoX-2B and CogVideo, offering powerful video generation capabilities. The repository offers tools for inference, fine-tuning, and model conversion, along with demos showcasing the model's capabilities through CLI, web UI, and online experiences. CogVideo aims to facilitate the creation of high-quality videos from textual descriptions, catering to a wide range of applications.

OpenCompass is a one-stop platform for large model evaluation, aiming to provide a fair, open, and reproducible benchmark for large model evaluation. Its main features include: * Comprehensive support for models and datasets: Pre-support for 20+ HuggingFace and API models, a model evaluation scheme of 70+ datasets with about 400,000 questions, comprehensively evaluating the capabilities of the models in five dimensions. * Efficient distributed evaluation: One line command to implement task division and distributed evaluation, completing the full evaluation of billion-scale models in just a few hours. * Diversified evaluation paradigms: Support for zero-shot, few-shot, and chain-of-thought evaluations, combined with standard or dialogue-type prompt templates, to easily stimulate the maximum performance of various models. * Modular design with high extensibility: Want to add new models or datasets, customize an advanced task division strategy, or even support a new cluster management system? Everything about OpenCompass can be easily expanded! * Experiment management and reporting mechanism: Use config files to fully record each experiment, and support real-time reporting of results.

llm-finetuning is a repository that provides a serverless twist to the popular axolotl fine-tuning library using Modal's serverless infrastructure. It allows users to quickly fine-tune any LLM model with state-of-the-art optimizations like Deepspeed ZeRO, LoRA adapters, Flash attention, and Gradient checkpointing. The repository simplifies the fine-tuning process by not exposing all CLI arguments, instead allowing users to specify options in a config file. It supports efficient training and scaling across multiple GPUs, making it suitable for production-ready fine-tuning jobs.

TornadoVM is a plug-in to OpenJDK and GraalVM that allows programmers to automatically run Java programs on heterogeneous hardware. TornadoVM targets OpenCL, PTX and SPIR-V compatible devices which include multi-core CPUs, dedicated GPUs (Intel, NVIDIA, AMD), integrated GPUs (Intel HD Graphics and ARM Mali), and FPGAs (Intel and Xilinx).

h2oGPT is an Apache V2 open-source project that allows users to query and summarize documents or chat with local private GPT LLMs. It features a private offline database of any documents (PDFs, Excel, Word, Images, Video Frames, Youtube, Audio, Code, Text, MarkDown, etc.), a persistent database (Chroma, Weaviate, or in-memory FAISS) using accurate embeddings (instructor-large, all-MiniLM-L6-v2, etc.), and efficient use of context using instruct-tuned LLMs (no need for LangChain's few-shot approach). h2oGPT also offers parallel summarization and extraction, reaching an output of 80 tokens per second with the 13B LLaMa2 model, HYDE (Hypothetical Document Embeddings) for enhanced retrieval based upon LLM responses, a variety of models supported (LLaMa2, Mistral, Falcon, Vicuna, WizardLM. With AutoGPTQ, 4-bit/8-bit, LORA, etc.), GPU support from HF and LLaMa.cpp GGML models, and CPU support using HF, LLaMa.cpp, and GPT4ALL models. Additionally, h2oGPT provides Attention Sinks for arbitrarily long generation (LLaMa-2, Mistral, MPT, Pythia, Falcon, etc.), a UI or CLI with streaming of all models, the ability to upload and view documents through the UI (control multiple collaborative or personal collections), Vision Models LLaVa, Claude-3, Gemini-Pro-Vision, GPT-4-Vision, Image Generation Stable Diffusion (sdxl-turbo, sdxl) and PlaygroundAI (playv2), Voice STT using Whisper with streaming audio conversion, Voice TTS using MIT-Licensed Microsoft Speech T5 with multiple voices and Streaming audio conversion, Voice TTS using MPL2-Licensed TTS including Voice Cloning and Streaming audio conversion, AI Assistant Voice Control Mode for hands-free control of h2oGPT chat, Bake-off UI mode against many models at the same time, Easy Download of model artifacts and control over models like LLaMa.cpp through the UI, Authentication in the UI by user/password via Native or Google OAuth, State Preservation in the UI by user/password, Linux, Docker, macOS, and Windows support, Easy Windows Installer for Windows 10 64-bit (CPU/CUDA), Easy macOS Installer for macOS (CPU/M1/M2), Inference Servers support (oLLaMa, HF TGI server, vLLM, Gradio, ExLLaMa, Replicate, OpenAI, Azure OpenAI, Anthropic), OpenAI-compliant, Server Proxy API (h2oGPT acts as drop-in-replacement to OpenAI server), Python client API (to talk to Gradio server), JSON Mode with any model via code block extraction. Also supports MistralAI JSON mode, Claude-3 via function calling with strict Schema, OpenAI via JSON mode, and vLLM via guided_json with strict Schema, Web-Search integration with Chat and Document Q/A, Agents for Search, Document Q/A, Python Code, CSV frames (Experimental, best with OpenAI currently), Evaluate performance using reward models, and Quality maintained with over 1000 unit and integration tests taking over 4 GPU-hours.

LightLLM is a Python-based LLM (Large Language Model) inference and serving framework known for its lightweight design, scalability, and high-speed performance. It offers features like tri-process asynchronous collaboration, Nopad for efficient attention operations, dynamic batch scheduling, FlashAttention integration, tensor parallelism, Token Attention for zero memory waste, and Int8KV Cache. The tool supports various models like BLOOM, LLaMA, StarCoder, Qwen-7b, ChatGLM2-6b, Baichuan-7b, Baichuan2-7b, Baichuan2-13b, InternLM-7b, Yi-34b, Qwen-VL, Llava-7b, Mixtral, Stablelm, and MiniCPM. Users can deploy and query models using the provided server launch commands and interact with multimodal models like QWen-VL and Llava using specific queries and images.

This project provides a comprehensive guide to fine-tuning large language models (LLMs) with efficient methods like LoRA and P-tuning V2. It includes detailed instructions, code examples, and performance benchmarks for various LLMs and fine-tuning techniques. The guide also covers data preparation, evaluation, prediction, and running inference on CPU environments. By leveraging this guide, users can effectively fine-tune LLMs for specific tasks and applications.

Mistral.rs is a fast LLM inference platform written in Rust. We support inference on a variety of devices, quantization, and easy-to-use application with an Open-AI API compatible HTTP server and Python bindings.

H2O LLM Studio is a framework and no-code GUI designed for fine-tuning state-of-the-art large language models (LLMs). With H2O LLM Studio, you can easily and effectively fine-tune LLMs without the need for any coding experience. The GUI is specially designed for large language models, and you can finetune any LLM using a large variety of hyperparameters. You can also use recent finetuning techniques such as Low-Rank Adaptation (LoRA) and 8-bit model training with a low memory footprint. Additionally, you can use Reinforcement Learning (RL) to finetune your model (experimental), use advanced evaluation metrics to judge generated answers by the model, track and compare your model performance visually, and easily export your model to the Hugging Face Hub and share it with the community.

Habitat-Sim is a high-performance physics-enabled 3D simulator with support for 3D scans of indoor/outdoor spaces, CAD models of spaces and piecewise-rigid objects, configurable sensors, robots described via URDF, and rigid-body mechanics. It prioritizes simulation speed over the breadth of simulation capabilities, achieving several thousand frames per second (FPS) running single-threaded and over 10,000 FPS multi-process on a single GPU when rendering a scene from the Matterport3D dataset. Habitat-Sim simulates a Fetch robot interacting in ReplicaCAD scenes at over 8,000 steps per second (SPS), where each ‘step’ involves rendering 1 RGBD observation (128×128 pixels) and rigid-body dynamics for 1/30sec.

MiniCPM-V is a series of end-side multimodal LLMs designed for vision-language understanding. The models take image and text inputs to provide high-quality text outputs. The series includes models like MiniCPM-Llama3-V 2.5 with 8B parameters surpassing proprietary models, and MiniCPM-V 2.0, a lighter model with 2B parameters. The models support over 30 languages, efficient deployment on end-side devices, and have strong OCR capabilities. They achieve state-of-the-art performance on various benchmarks and prevent hallucinations in text generation. The models can process high-resolution images efficiently and support multilingual capabilities.

Generative Fusion Decoding (GFD) is a novel shallow fusion framework that integrates Large Language Models (LLMs) into multi-modal text recognition systems such as automatic speech recognition (ASR) and optical character recognition (OCR). GFD operates across mismatched token spaces of different models by mapping text token space to byte token space, enabling seamless fusion during the decoding process. It simplifies the complexity of aligning different model sample spaces, allows LLMs to correct errors in tandem with the recognition model, increases robustness in long-form speech recognition, and enables fusing recognition models deficient in Chinese text recognition with LLMs extensively trained on Chinese. GFD significantly improves performance in ASR and OCR tasks, offering a unified solution for leveraging existing pre-trained models through step-by-step fusion.

Meet the Restaurant Startup Guide GPT: your friendly guide in the restaurant biz. It offers casual, approachable advice to help you start and run your own restaurant with ease.

UNIX terminal responses with OS process visuals. (on or off) [off] by default until GPT-4 behaves better... Bash profiles and advanced memory system for realistic bash simulation. V1 (beta)

Design your perfect race calendar and training plans for your next race.

Bash terminal emulator with code-block responses

A helpful coach for guiding teams through Design Sprints with a touch of sass.

Replies with only the WebStorm macOS shortcut

Assists with Qiskit code and quantum computing concepts.

aids preparing for and running Trust Pods with excellence

Dynamic D&D expert with narrative and rules mastery.

Guiding your product journey with expert insights. Made by the team behind kraftful.com

Enhance D&D campaigns with Roll20 setup and custom token creation.

Imaginative RPG campaign creator with visual aids.

Expert social media marketing advisor with up-to-date insights and strategies.

Explains Pathfinder 2e rules with direct links.

Interactive RPG guide for personalized fantasy adventures with elements of chance.

A creative, engaging DnD DM with a unique, personal tone

Your expert guide for all things EUC, with a focus on battery safety, maintenance, and protective gear.

DungeonRules GPT demystifies D&D and RPG rules, providing clear explanations with examples.

Expert in Google's ad campaigns and digital marketing, hip and cool in style. In touch with the social web.

I provide Cairo coding help based on my knowledge docs.