Best AI tools for< Run Inference On Device >

Qualcomm AI Hub is a platform that allows users to run AI models on Snapdragon® 8 Elite devices. It provides a collaborative ecosystem for model makers, cloud providers, runtime, and SDK partners to deploy on-device AI solutions quickly and efficiently. Users can bring their own models, optimize for deployment, and access a variety of AI services and resources. The platform caters to various industries such as mobile, automotive, and IoT, offering a range of models and services for edge computing.

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.

Groq is a fast AI inference tool that offers GroqCloud™ Platform and GroqRack™ Cluster for developers to build and deploy AI models with ultra-low-latency inference. It provides instant intelligence for openly-available models like Llama 3.1 and is known for its speed and compatibility with other AI providers. Groq powers leading openly-available AI models and has gained recognition in the AI chip industry. The tool has received significant funding and valuation, positioning itself as a strong challenger to established players like Nvidia.

fal.ai is a generative media platform designed for developers to build the next generation of creativity. It offers lightning-fast inference, access to high-quality generative media models, and optimization by the fal Inference Engine™. Developers can fine-tune their own models, leverage the fastest AI inference engine for diffusion models, and benefit from the best LoRA trainer in the industry for FLUX. The platform provides a world-class developer experience and cost-effective scalability based on actual usage.

TitanML is a platform that provides tools and services for deploying and scaling Generative AI applications. Their flagship product, the Titan Takeoff Inference Server, helps machine learning engineers build, deploy, and run Generative AI models in secure environments. TitanML's platform is designed to make it easy for businesses to adopt and use Generative AI, without having to worry about the underlying infrastructure. With TitanML, businesses can focus on building great products and solving real business problems.

Tensoic AI is an AI tool designed for custom Large Language Models (LLMs) fine-tuning and inference. It offers ultra-fast fine-tuning and inference capabilities for enterprise-grade LLMs, with a focus on use case-specific tasks. The tool is efficient, cost-effective, and easy to use, enabling users to outperform general-purpose LLMs using synthetic data. Tensoic AI generates small, powerful models that can run on consumer-grade hardware, making it ideal for a wide range of applications.

Mystic.ai is an AI tool designed to deploy and scale Machine Learning models with ease. It offers a fully managed Kubernetes platform that runs in your own cloud, allowing users to deploy ML models in their own Azure/AWS/GCP account or in a shared GPU cluster. Mystic.ai provides cost optimizations, fast inference, simpler developer experience, and performance optimizations to ensure high-performance AI model serving. With features like pay-as-you-go API, cloud integration with AWS/Azure/GCP, and a beautiful dashboard, Mystic.ai simplifies the deployment and management of ML models for data scientists and AI engineers.

Cortex Labs is a decentralized world computer that enables AI and AI-powered decentralized applications (dApps) to run on the blockchain. It offers a Layer2 solution called ZkMatrix, which utilizes zkRollup technology to enhance transaction speed and reduce fees. Cortex Virtual Machine (CVM) supports on-chain AI inference using GPU, ensuring deterministic results across computing environments. Cortex also enables machine learning in smart contracts and dApps, fostering an open-source ecosystem for AI researchers and developers to share models. The platform aims to solve the challenge of on-chain machine learning execution efficiently and deterministically, providing tools and resources for developers to integrate AI into blockchain applications.

RunPod is a cloud platform specifically designed for AI development and deployment. It offers a range of features to streamline the process of developing, training, and scaling AI models, including a library of pre-built templates, efficient training pipelines, and scalable deployment options. RunPod also provides access to a wide selection of GPUs, allowing users to choose the optimal hardware for their specific AI workloads.

GPUX is a cloud platform that provides access to GPUs for running AI workloads. It offers a variety of features to make it easy to deploy and run AI models, including a user-friendly interface, pre-built templates, and support for a variety of programming languages. GPUX is also committed to providing a sustainable and ethical platform, and it has partnered with organizations such as the Climate Leadership Council to reduce its carbon footprint.

Together AI is an AI tool that offers a variety of generative AI services, including serverless models, fine-tuning capabilities, dedicated endpoints, and GPU clusters. Users can run or fine-tune leading open source models with only a few lines of code. The platform provides a range of functionalities for tasks such as chat, vision, text-to-speech, code/language reranking, and more. Together AI aims to simplify the process of utilizing AI models for various applications.

Modal is a high-performance cloud platform designed for developers, AI data, and ML teams. It offers a serverless environment for running generative AI models, large-scale batch jobs, job queues, and more. With Modal, users can bring their own code and leverage the platform's optimized container file system for fast cold boots and seamless autoscaling. The platform is engineered for large-scale workloads, allowing users to scale to hundreds of GPUs, pay only for what they use, and deploy functions to the cloud in seconds without the need for YAML or Dockerfiles. Modal also provides features for job scheduling, web endpoints, observability, and security compliance.

Awan LLM is an AI tool that offers an Unlimited Tokens, Unrestricted, and Cost-Effective LLM Inference API Platform for Power Users and Developers. It allows users to generate unlimited tokens, use LLM models without constraints, and pay per month instead of per token. The platform features an AI Assistant, AI Agents, Roleplay with AI companions, Data Processing, Code Completion, and Applications for profitable AI-powered applications.

SWE Kit is an open-source headless IDE designed for building custom coding agents with state-of-the-art performance. It offers AI-native tools to streamline the coding review process, enhance code quality, and optimize development efficiency. The application supports various agentic frameworks and LLM inference providers, providing a flexible runtime environment for seamless codebase interaction. With features like code analysis, code indexing, and third-party service integrations, SWE Kit empowers developers to create and run coding agents effortlessly.

BentoML is a platform for software engineers to build, ship, and scale AI products. It provides a unified AI application framework that makes it easy to manage and version models, create service APIs, and build and run AI applications anywhere. BentoML is used by over 1000 organizations and has a global community of over 3000 members.

The Run Recommender is a web-based tool that helps runners find the perfect pair of running shoes. It uses a smart algorithm to suggest options based on your input, giving you a starting point in your search for the perfect pair. The Run Recommender is designed to be user-friendly and easy to use. Simply input your shoe width, age, weight, and other details, and the Run Recommender will generate a list of potential shoes that might suit your running style and body. You can also provide information about your running experience, distance, and frequency, and the Run Recommender will use this information to further refine its suggestions. Once you have a list of potential shoes, you can click on each shoe to learn more about it, including its features, benefits, and price. You can also search for the shoe on Amazon to find the best deals.

Practice Run AI is an online platform that offers AI-powered tools for various tasks. Users can utilize the application to practice and run AI algorithms without the need for complex setups or installations. The platform provides a user-friendly interface that allows individuals to experiment with AI models and enhance their understanding of artificial intelligence concepts. Practice Run AI aims to democratize AI education and make it accessible to a wider audience by simplifying the learning process and providing hands-on experience.

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.

Reflect is an AI-powered test automation tool that revolutionizes the way end-to-end tests are created, executed, and maintained. By leveraging Generative AI, Reflect eliminates the need for manual coding and provides a seamless testing experience. The tool offers features such as no-code test automation, visual testing, API testing, cross-browser testing, and more. Reflect aims to help companies increase software quality by accelerating testing processes and ensuring test adaptability over time.

The website is a comprehensive resource hub for learning and mastering end-to-end testing using the Playwright automation framework. It offers a variety of content such as blog posts, tutorials, videos, and a QA Wiki with definitions of common testing terms. Users can also ask questions related to Playwright and access a Discord forum for discussions. Additionally, there is a browser extension available for generating Playwright locators, and a section dedicated to QA jobs and automation opportunities.

Nexa SDK is a comprehensive toolkit supporting ONNX and GGML models for text generation, image generation, vision-language models (VLM), and text-to-speech (TTS) capabilities. It offers an OpenAI-compatible API server with JSON schema mode and streaming support, along with a user-friendly Streamlit UI. Users can run Nexa SDK on any device with Python environment, with GPU acceleration supported. The toolkit provides model support, conversion engine, inference engine for various tasks, and differentiating features from other tools.

This repository provides support for inference RWKV models on Qualcomm HTP (Hexagon Tensor Processor) using QNN SDK. It supports RWKV v5, v6, and experimentally v7 models, inference using Qualcomm CPU, GPU, or HTP as the backend, whole-model float16 inference, activation INT16 and weights INT8 quantized inference, and activation INT16 and weights INT4/INT8 mixed quantized inference. Users can convert model weights to QNN model library files, generate HTP context cache, and run inference on Qualcomm Snapdragon SM8650 with HTP v75. The project requires QNN SDK, AIMET toolkit, and specific hardware for verification.

Awesome Generative AI is a curated list of modern Generative Artificial Intelligence projects and services. Generative AI technology creates original content like images, sounds, and texts using machine learning algorithms trained on large data sets. It can produce unique and realistic outputs such as photorealistic images, digital art, music, and writing. The repo covers a wide range of applications in art, entertainment, marketing, academia, and computer science.

AITreasureBox is a comprehensive collection of AI tools and resources designed to simplify and accelerate the development of AI projects. It provides a wide range of pre-trained models, datasets, and utilities that can be easily integrated into various AI applications. With AITreasureBox, developers can quickly prototype, test, and deploy AI solutions without having to build everything from scratch. Whether you are working on computer vision, natural language processing, or reinforcement learning projects, AITreasureBox has something to offer for everyone. The repository is regularly updated with new tools and resources to keep up with the latest advancements in the field of artificial intelligence.

TPI-LLM (Tensor Parallelism Inference for Large Language Models) is a system designed to bring LLM functions to low-resource edge devices, addressing privacy concerns by enabling LLM inference on edge devices with limited resources. It leverages multiple edge devices for inference through tensor parallelism and a sliding window memory scheduler to minimize memory usage. TPI-LLM demonstrates significant improvements in TTFT and token latency compared to other models, and plans to support infinitely large models with low token latency in the future.

Distributed Llama is a tool that allows you to run large language models (LLMs) on weak devices or make powerful devices even more powerful by distributing the workload and dividing the RAM usage. It uses TCP sockets to synchronize the state of the neural network, and you can easily configure your AI cluster by using a home router. Distributed Llama supports models such as Llama 2 (7B, 13B, 70B) chat and non-chat versions, Llama 3, and Grok-1 (314B).

T-MAC is a kernel library that directly supports mixed-precision matrix multiplication without the need for dequantization by utilizing lookup tables. It aims to boost low-bit LLM inference on CPUs by offering support for various low-bit models. T-MAC achieves significant speedup compared to SOTA CPU low-bit framework (llama.cpp) and can even perform well on lower-end devices like Raspberry Pi 5. The tool demonstrates superior performance over existing low-bit GEMM kernels on CPU, reduces power consumption, and provides energy savings. It achieves comparable performance to CUDA GPU on certain tasks while delivering considerable power and energy savings. T-MAC's method involves using lookup tables to support mpGEMM and employs key techniques like precomputing partial sums, shift and accumulate operations, and utilizing tbl/pshuf instructions for fast table lookup.

ReVA (Reverse Engineering Assistant) is a project aimed at building a disassembler agnostic AI assistant for reverse engineering tasks. It utilizes a tool-driven approach, providing small tools to the user to empower them in completing complex tasks. The assistant is designed to accept various inputs, guide the user in correcting mistakes, and provide additional context to encourage exploration. Users can ask questions, perform tasks like decompilation, class diagram generation, variable renaming, and more. ReVA supports different language models for online and local inference, with easy configuration options. The workflow involves opening the RE tool and program, then starting a chat session to interact with the assistant. Installation includes setting up the Python component, running the chat tool, and configuring the Ghidra extension for seamless integration. ReVA aims to enhance the reverse engineering process by breaking down actions into small parts, including the user's thoughts in the output, and providing support for monitoring and adjusting prompts.

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.

Okay, here is a JSON object with the requested information about the awesome-cuda-tensorrt-fpga repository:

AiTreasureBox is a versatile AI tool that provides a collection of pre-trained models and algorithms for various machine learning tasks. It simplifies the process of implementing AI solutions by offering ready-to-use components that can be easily integrated into projects. With AiTreasureBox, users can quickly prototype and deploy AI applications without the need for extensive knowledge in machine learning or deep learning. The tool covers a wide range of tasks such as image classification, text generation, sentiment analysis, object detection, and more. It is designed to be user-friendly and accessible to both beginners and experienced developers, making AI development more efficient and accessible to a wider audience.

The LlamaEdge project makes it easy to run LLM inference apps and create OpenAI-compatible API services for the Llama2 series of LLMs locally. It provides a Rust+Wasm stack for fast, portable, and secure LLM inference on heterogeneous edge devices. The project includes source code for text generation, chatbot, and API server applications, supporting all LLMs based on the llama2 framework in the GGUF format. LlamaEdge is committed to continuously testing and validating new open-source models and offers a list of supported models with download links and startup commands. It is cross-platform, supporting various OSes, CPUs, and GPUs, and provides troubleshooting tips for common errors.

ChatGLM.cpp is a C++ implementation of ChatGLM-6B, ChatGLM2-6B, ChatGLM3-6B and more LLMs for real-time chatting on your MacBook. It is based on ggml, working in the same way as llama.cpp. ChatGLM.cpp features accelerated memory-efficient CPU inference with int4/int8 quantization, optimized KV cache and parallel computing. It also supports P-Tuning v2 and LoRA finetuned models, streaming generation with typewriter effect, Python binding, web demo, api servers and more possibilities.

The 'awesome-local-llms' repository is a curated list of open-source tools for local Large Language Model (LLM) inference, covering both proprietary and open weights LLMs. The repository categorizes these tools into LLM inference backend engines, LLM front end UIs, and all-in-one desktop applications. It collects GitHub repository metrics as proxies for popularity and active maintenance. Contributions are encouraged, and users can suggest additional open-source repositories through the Issues section or by running a provided script to update the README and make a pull request. The repository aims to provide a comprehensive resource for exploring and utilizing local LLM tools.

Torchtune is a PyTorch-native library for easily authoring, fine-tuning, and experimenting with LLMs. It provides native-PyTorch implementations of popular LLMs using composable and modular building blocks, easy-to-use and hackable training recipes for popular fine-tuning techniques, YAML configs for easily configuring training, evaluation, quantization, or inference recipes, and built-in support for many popular dataset formats and prompt templates to help you quickly get started with training.

Java & Python programming assistant for AI model inference.

run the embedded code

Run mock interviews, review content and get tips to ace strategy consulting and investment banking interviews

Run Golang code in ChatGPT

I help create and run productive design thinking sessions.

Download and Run Open Source LLMs Locally.

Your new DM's screen: helping Dungeon Masters to craft & run amazing D&D adventures.

Hosts a real SQLite database and helps you create tables, make schema changes, and run SQL queries, ideal for all levels of database administration.

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.

A community-building GPT based on the wildly popular Community Design™ framework from Mighty Networks. Start creating communities that run themselves.

Friendly web assistant for efficient code. Ask the wizard to create an application and you will get the HTML, CSS and Javascript code ready to run your web application.

Find trails that fit your nature for your next hike, ride, or run.

I'm your brainstorm muse in marketing and advertising; the creativity machine you need to sharpen the skills, land the job, generate the ideas, win the pitches, build the brands, ace the awards, or even run your own agency. Psst... don't let your clients find out about me! 😉

Provides running splits for Strava Routes, accounting for distance and elevation changes

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

Creative naming assistant for product developers

Manages office supplies to ensure smooth operations.

Giveaway bot for managing and drawing giveaway winners

「走れメロス」のメロスになりきって回答します。