Best AI tools for< Offload Cpu Tasks >

Juice Remote GPU is a software that enables AI and Graphics workloads on remote GPUs. It allows users to offload GPU processing for any CUDA or Vulkan application to a remote host running the Juice agent. The software injects CUDA and Vulkan implementations during runtime, eliminating the need for code changes in the application. Juice supports multiple clients connecting to multiple GPUs and multiple clients sharing a single GPU. It is useful for sharing a single GPU across multiple workstations, allocating GPUs dynamically to CPU-only machines, and simplifying development workflows and deployments. Juice Remote GPU performs within 5% of a local GPU when running in the same datacenter. It supports various APIs, including CUDA, Vulkan, DirectX, and OpenGL, and is compatible with PyTorch and TensorFlow. The team behind Juice Remote GPU consists of engineers from Meta, Intel, and the gaming industry.

Cykel AI is an AI co-pilot designed to assist users in automating various digital tasks. It interacts with any website to complete complex tasks based on user instructions, allowing users to offload 50% of their to-do list to AI. From sending emails to updating spreadsheets, Cykel offers a seamless way to streamline digital workflows and boost productivity. With features like autonomous learning, scalable parallel tasking, and the ability to create and share shortcuts, Cykel aims to revolutionize task automation for individuals and teams across different industries.

SmileDial is a natural dental AI receptionist designed for Canadian dental practices. It offers a 24/7 AI receptionist system to help dentists save time, reduce costs, and enhance patient satisfaction. The AI-driven receptionist, named Susan, assists in real-time scheduling, automated reminders, insurance checks, and PHIPA compliance. SmileDial aims to maximize bookings, decrease no-shows, and offload time-consuming tasks, ultimately improving the efficiency and patient experience in dental offices.

Prime is a framework for efficient, globally distributed training of AI models over the internet. It includes features such as fault-tolerant training with ElasticDeviceMesh, asynchronous distributed checkpointing, live checkpoint recovery, custom Int8 All-Reduce Kernel, maximizing bandwidth utilization, PyTorch FSDP2/DTensor ZeRO-3 implementation, and CPU off-loading. The framework aims to optimize communication, checkpointing, and bandwidth utilization for large-scale AI model training.

Mosec is a high-performance and flexible model serving framework for building ML model-enabled backend and microservices. It bridges the gap between any machine learning models you just trained and the efficient online service API. * **Highly performant** : web layer and task coordination built with Rust 🦀, which offers blazing speed in addition to efficient CPU utilization powered by async I/O * **Ease of use** : user interface purely in Python 🐍, by which users can serve their models in an ML framework-agnostic manner using the same code as they do for offline testing * **Dynamic batching** : aggregate requests from different users for batched inference and distribute results back * **Pipelined stages** : spawn multiple processes for pipelined stages to handle CPU/GPU/IO mixed workloads * **Cloud friendly** : designed to run in the cloud, with the model warmup, graceful shutdown, and Prometheus monitoring metrics, easily managed by Kubernetes or any container orchestration systems * **Do one thing well** : focus on the online serving part, users can pay attention to the model optimization and business logic

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.

This repository does not provide a tool, but rather a collection of resources and strategies for academics in the field of artificial intelligence who are feeling depressed or overwhelmed by the rapid advancements in the field. The resources include articles, blog posts, and other materials that offer advice on how to cope with the challenges of working in a fast-paced and competitive environment.

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

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.

Simplifine is an open-source library designed for easy LLM finetuning, enabling users to perform tasks such as supervised fine tuning, question-answer finetuning, contrastive loss for embedding tasks, multi-label classification finetuning, and more. It provides features like WandB logging, in-built evaluation tools, automated finetuning parameters, and state-of-the-art optimization techniques. The library offers bug fixes, new features, and documentation updates in its latest version. Users can install Simplifine via pip or directly from GitHub. The project welcomes contributors and provides comprehensive documentation and support for users.

RTL-Coder is a tool designed to outperform GPT-3.5 in RTL code generation by providing a fully open-source dataset and a lightweight solution. It targets Verilog code generation and offers an automated flow to generate a large labeled dataset with over 27,000 diverse Verilog design problems and answers. The tool addresses the data availability challenge in IC design-related tasks and can be used for various applications beyond LLMs. The tool includes four RTL code generation models available on the HuggingFace platform, each with specific features and performance characteristics. Additionally, RTL-Coder introduces a new LLM training scheme based on code quality feedback to further enhance model performance and reduce GPU memory consumption.

llm-resource is a comprehensive collection of high-quality resources for Large Language Models (LLM). It covers various aspects of LLM including algorithms, training, fine-tuning, alignment, inference, data engineering, compression, evaluation, prompt engineering, AI frameworks, AI basics, AI infrastructure, AI compilers, LLM application development, LLM operations, AI systems, and practical implementations. The repository aims to gather and share valuable resources related to LLM for the community to benefit from.

FlexFlow Serve is an open-source compiler and distributed system for **low latency**, **high performance** LLM serving. FlexFlow Serve outperforms existing systems by 1.3-2.0x for single-node, multi-GPU inference and by 1.4-2.4x for multi-node, multi-GPU inference.

HF-Waitress is a powerful server application for deploying and interacting with HuggingFace Transformer models. It simplifies running open-source Large Language Models (LLMs) locally on-device, providing on-the-fly quantization via BitsAndBytes, HQQ, and Quanto. It requires no manual model downloads, offers concurrency, streaming responses, and supports various hardware and platforms. The server uses a `config.json` file for easy configuration management and provides detailed error handling and logging.

Beta9 is an open-source platform for running scalable serverless GPU workloads across cloud providers. It allows users to scale out workloads to thousands of GPU or CPU containers, achieve ultrafast cold-start for custom ML models, automatically scale to zero to pay for only what is used, utilize flexible distributed storage, distribute workloads across multiple cloud providers, and easily deploy task queues and functions using simple Python abstractions. The platform is designed for launching remote serverless containers quickly, featuring a custom, lazy loading image format backed by S3/FUSE, a fast redis-based container scheduling engine, content-addressed storage for caching images and files, and a custom runc container runtime.

SWIFT (Scalable lightWeight Infrastructure for Fine-Tuning) supports training, inference, evaluation and deployment of nearly **200 LLMs and MLLMs** (multimodal large models). Developers can directly apply our framework to their own research and production environments to realize the complete workflow from model training and evaluation to application. In addition to supporting the lightweight training solutions provided by [PEFT](https://github.com/huggingface/peft), we also provide a complete **Adapters library** to support the latest training techniques such as NEFTune, LoRA+, LLaMA-PRO, etc. This adapter library can be used directly in your own custom workflow without our training scripts. To facilitate use by users unfamiliar with deep learning, we provide a Gradio web-ui for controlling training and inference, as well as accompanying deep learning courses and best practices for beginners. Additionally, we are expanding capabilities for other modalities. Currently, we support full-parameter training and LoRA training for AnimateDiff.

LoRAX is a framework that allows users to serve thousands of fine-tuned models on a single GPU, dramatically reducing the cost of serving without compromising on throughput or latency. It features dynamic adapter loading, heterogeneous continuous batching, adapter exchange scheduling, optimized inference, and is ready for production with prebuilt Docker images, Helm charts for Kubernetes, Prometheus metrics, and distributed tracing with Open Telemetry. LoRAX supports a number of Large Language Models as the base model including Llama, Mistral, and Qwen, and any of the linear layers in the model can be adapted via LoRA and loaded in LoRAX.

This GitHub repository contains examples of fine-tuning open source large language models. It showcases the process of fine-tuning and quantizing large language models using efficient techniques like Lora and QLora. The repository serves as a practical guide for individuals looking to optimize the performance of language models through fine-tuning.

The fsdp_qlora repository provides a script for training Large Language Models (LLMs) with Quantized LoRA and Fully Sharded Data Parallelism (FSDP). It integrates FSDP+QLoRA into the Axolotl platform and offers installation instructions for dependencies like llama-recipes, fastcore, and PyTorch. Users can finetune Llama-2 70B on Dual 24GB GPUs using the provided command. The script supports various training options including full params fine-tuning, LoRA fine-tuning, custom LoRA fine-tuning, quantized LoRA fine-tuning, and more. It also discusses low memory loading, mixed precision training, and comparisons to existing trainers. The repository addresses limitations and provides examples for training with different configurations, including BnB QLoRA and HQQ QLoRA. Additionally, it offers SLURM training support and instructions for adding support for a new model.

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.