surogate

Surogate is a high-performance, mixed-precision LLM pre-training and fine-tuning framework designed for practical hardware limits. It combines a native C++/CUDA execution engine, a low-overhead Python frontend, and a highly optimized multi-threaded scheduler to achieve industry-leading Speed-Of-Light (SOL) utilization on NVIDIA GPUs. Surogate Studio is the no-code companion for enterprise-grade LLMOps, offering features like pre-training, fine-tuning, native multi-GPU and multi-Node training, smart CPU offloading, pre-built training recipes, mixed-precision training, and adaptive training. It supports various NVIDIA GPUs and provides a unified platform for managing AI infrastructure and operations.

Transformer Lab is an app that allows users to experiment with Large Language Models by providing features such as one-click download of popular models, finetuning across different hardware, RLHF and Preference Optimization, working with LLMs across different operating systems, chatting with models, using different inference engines, evaluating models, building datasets for training, calculating embeddings, providing a full REST API, running in the cloud, converting models across platforms, supporting plugins, embedded Monaco code editor, prompt editing, inference logs, all through a simple cross-platform GUI.

ExecuTorch is an end-to-end solution for enabling on-device inference capabilities across mobile and edge devices including wearables, embedded devices and microcontrollers. It is part of the PyTorch Edge ecosystem and enables efficient deployment of PyTorch models to edge devices. Key value propositions of ExecuTorch are: * **Portability:** Compatibility with a wide variety of computing platforms, from high-end mobile phones to highly constrained embedded systems and microcontrollers. * **Productivity:** Enabling developers to use the same toolchains and SDK from PyTorch model authoring and conversion, to debugging and deployment to a wide variety of platforms. * **Performance:** Providing end users with a seamless and high-performance experience due to a lightweight runtime and utilizing full hardware capabilities such as CPUs, NPUs, and DSPs.

FlashInfer is a library for Language Languages Models that provides high-performance implementation of LLM GPU kernels such as FlashAttention, PageAttention and LoRA. FlashInfer focus on LLM serving and inference, and delivers state-the-art performance across diverse scenarios.

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.

NodeTool is a platform designed for AI enthusiasts, developers, and creators, providing a visual interface to access a variety of AI tools and models. It simplifies access to advanced AI technologies, offering resources for content creation, data analysis, automation, and more. With features like a visual editor, seamless integration with leading AI platforms, model manager, and API integration, NodeTool caters to both newcomers and experienced users in the AI field.

The stable-diffusion.cpp repository provides an implementation for inferring stable diffusion in pure C/C++. It offers features such as support for different versions of stable diffusion, lightweight and dependency-free implementation, various quantization support, memory-efficient CPU inference, GPU acceleration, and more. Users can download the built executable program or build it manually. The repository also includes instructions for downloading weights, building from scratch, using different acceleration methods, running the tool, converting weights, and utilizing various features like Flash Attention, ESRGAN upscaling, PhotoMaker support, and more. Additionally, it mentions future TODOs and provides information on memory requirements, bindings, UIs, contributors, and references.

Jan is an open-source ChatGPT alternative that runs 100% offline on your computer. It supports universal architectures, including Nvidia GPUs, Apple M-series, Apple Intel, Linux Debian, and Windows x64. Jan is currently in development, so expect breaking changes and bugs. It is lightweight and embeddable, and can be used on its own within your own projects.

LightEval is a lightweight LLM evaluation suite that Hugging Face has been using internally with the recently released LLM data processing library datatrove and LLM training library nanotron. We're releasing it with the community in the spirit of building in the open. Note that it is still very much early so don't expect 100% stability ^^' In case of problems or question, feel free to open an issue!

Local Cocoa is a privacy-focused tool that runs entirely on your device, turning files into memory to spark insights and power actions. It offers features like fully local privacy, multimodal memory, vector-powered retrieval, intelligent indexing, vision understanding, hardware acceleration, focused user experience, integrated notes, and auto-sync. The tool combines file ingestion, intelligent chunking, and local retrieval to build a private on-device knowledge system. The ultimate goal includes more connectors like Google Drive integration, voice mode for local speech-to-text interaction, and a plugin ecosystem for community tools and agents. Local Cocoa is built using Electron, React, TypeScript, FastAPI, llama.cpp, and Qdrant.

OrchestKit is a powerful and flexible orchestration tool designed to streamline and automate complex workflows. It provides a user-friendly interface for defining and managing orchestration tasks, allowing users to easily create, schedule, and monitor workflows. With support for various integrations and plugins, OrchestKit enables seamless automation of tasks across different systems and applications. Whether you are a developer looking to automate deployment processes or a system administrator managing complex IT operations, OrchestKit offers a comprehensive solution to simplify and optimize your workflow management.

Shimmy is a 5.1MB single-binary local inference server providing OpenAI-compatible endpoints for GGUF models. It offers fast, reliable AI inference with sub-second responses, zero configuration, and automatic port management. Perfect for developers seeking privacy, cost-effectiveness, speed, and easy integration with popular tools like VSCode and Cursor. Shimmy is designed to be invisible infrastructure that simplifies local AI development and deployment.

sandboxed.sh is a self-hosted cloud orchestrator for AI coding agents that provides isolated Linux workspaces with Claude Code, OpenCode & Amp runtimes. It allows users to hand off entire development cycles, run multi-day operations unattended, and keep sensitive data local by analyzing data against scientific literature. The tool features dual runtime support, mission control for remote agent management, isolated workspaces, a git-backed library, MCP registry, and multi-platform support with a web dashboard and iOS app.

Alphora is a full-stack framework for building production AI agents, providing agent orchestration, prompt engineering, tool execution, memory management, streaming, and deployment with an async-first, OpenAI-compatible design. It offers features like agent derivation, reasoning-action loop, async streaming, visual debugger, OpenAI compatibility, multimodal support, tool system with zero-config tools and type safety, prompt engine with dynamic prompts, memory and storage management, sandbox for secure execution, deployment as API, and more. Alphora allows users to build sophisticated AI agents easily and efficiently.

SINQ (Sinkhorn-Normalized Quantization) is a novel, fast, and high-quality quantization method designed to make any Large Language Models smaller while keeping their accuracy almost intact. It offers a model-agnostic quantization technique that delivers state-of-the-art performance for Large Language Models without sacrificing accuracy. With SINQ, users can deploy models that would otherwise be too big, drastically reducing memory usage while preserving LLM quality. The tool quantizes models using dual scaling for better quantization and achieves a more even error distribution, leading to stable behavior across layers and consistently higher accuracy even at very low bit-widths.

OpenResearcher is a fully open agentic large language model designed for long-horizon deep research scenarios. It achieves an impressive 54.8% accuracy on BrowseComp-Plus, surpassing performance of GPT-4.1, Claude-Opus-4, Gemini-2.5-Pro, DeepSeek-R1, and Tongyi-DeepResearch. The tool is fully open-source, providing the training and evaluation recipe—including data, model, training methodology, and evaluation framework for everyone to progress deep research. It offers features like a fully open-source recipe, highly scalable and low-cost generation of deep research trajectories, and remarkable performance on deep research benchmarks.

Surogate is a high-performance, mixed-precision LLM pre-training and fine-tuning framework designed for practical hardware limits. It combines a native C++/CUDA execution engine, a low-overhead Python frontend, and a highly optimized multi-threaded scheduler to achieve industry-leading Speed-Of-Light (SOL) utilization on NVIDIA GPUs. Surogate Studio is the no-code companion for enterprise-grade LLMOps, offering features like pre-training, fine-tuning, native multi-GPU and multi-Node training, smart CPU offloading, pre-built training recipes, mixed-precision training, and adaptive training. It supports various NVIDIA GPUs and provides a unified platform for managing AI infrastructure and operations.

MindsDB is a platform for customizing AI from enterprise data. You can create, serve, and fine-tune models in real-time from your database, vector store, and application data. MindsDB "enhances" SQL syntax with AI capabilities to make it accessible for developers worldwide. With MindsDB’s nearly 200 integrations, any developer can create AI customized for their purpose, faster and more securely. Their AI systems will constantly improve themselves — using companies’ own data, in real-time.

Kubeflow Training Operator is a Kubernetes-native project for fine-tuning and scalable distributed training of machine learning (ML) models created with various ML frameworks such as PyTorch, Tensorflow, XGBoost, MPI, Paddle and others. Training Operator allows you to use Kubernetes workloads to effectively train your large models via Kubernetes Custom Resources APIs or using Training Operator Python SDK. > Note: Before v1.2 release, Kubeflow Training Operator only supports TFJob on Kubernetes. * For a complete reference of the custom resource definitions, please refer to the API Definition. * TensorFlow API Definition * PyTorch API Definition * Apache MXNet API Definition * XGBoost API Definition * MPI API Definition * PaddlePaddle API Definition * For details of all-in-one operator design, please refer to the All-in-one Kubeflow Training Operator * For details on its observability, please refer to the monitoring design doc.

HelixML is a private GenAI platform that allows users to deploy the best of open AI in their own data center or VPC while retaining complete data security and control. It includes support for fine-tuning models with drag-and-drop functionality. HelixML brings the best of open source AI to businesses in an ergonomic and scalable way, optimizing the tradeoff between GPU memory and latency.

NNtrainer is a software framework for training neural network models on devices with limited resources. It enables on-device fine-tuning of neural networks using user data for personalization. NNtrainer supports various machine learning algorithms and provides examples for tasks such as few-shot learning, ResNet, VGG, and product rating. It is optimized for embedded devices and utilizes CBLAS and CUBLAS for accelerated calculations. NNtrainer is open source and released under the Apache License version 2.0.

Petals is a tool that allows users to run large language models at home in a BitTorrent-style manner. It enables fine-tuning and inference up to 10x faster than offloading. Users can generate text with distributed models like Llama 2, Falcon, and BLOOM, and fine-tune them for specific tasks directly from their desktop computer or Google Colab. Petals is a community-run system that relies on people sharing their GPUs to increase its capacity and offer a distributed network for hosting model layers.

This repository, LLaVA++, extends the visual capabilities of the LLaVA 1.5 model by incorporating the latest LLMs, Phi-3 Mini Instruct 3.8B, and LLaMA-3 Instruct 8B. It provides various models for instruction-following LMMS and academic-task-oriented datasets, along with training scripts for Phi-3-V and LLaMA-3-V. The repository also includes installation instructions and acknowledgments to related open-source contributions.

KULLM (구름) is a Korean Large Language Model developed by Korea University NLP & AI Lab and HIAI Research Institute. It is based on the upstage/SOLAR-10.7B-v1.0 model and has been fine-tuned for instruction. The model has been trained on 8×A100 GPUs and is capable of generating responses in Korean language. KULLM exhibits hallucination and repetition phenomena due to its decoding strategy. Users should be cautious as the model may produce inaccurate or harmful results. Performance may vary in benchmarks without a fixed system prompt.

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.

LitServe is a high-throughput serving engine designed for deploying AI models at scale. It generates an API endpoint for models, handles batching, streaming, and autoscaling across CPU/GPUs. LitServe is built for enterprise scale with a focus on minimal, hackable code-base without bloat. It supports various model types like LLMs, vision, time-series, and works with frameworks like PyTorch, JAX, Tensorflow, and more. The tool allows users to focus on model performance rather than serving boilerplate, providing full control and flexibility.

This repository documents how to optimize common algorithms based on CUDA. It includes subdirectories with code implementations for specific optimizations. The optimizations cover topics such as compiling PyTorch from source, NVIDIA's reduce optimization, OneFlow's elementwise template, fast atomic add for half data types, upsample nearest2d optimization in OneFlow, optimized indexing in PyTorch, OneFlow's softmax kernel, linear attention optimization, and more. The repository also includes learning resources related to deep learning frameworks, compilers, and optimization techniques.

AIAC is a library and command line tool to generate Infrastructure as Code (IaC) templates, configurations, utilities, queries, and more via LLM providers such as OpenAI, Amazon Bedrock, and Ollama. Users can define multiple 'backends' targeting different LLM providers and environments using a simple configuration file. The tool allows users to ask a model to generate templates for different scenarios and composes an appropriate request to the selected provider, storing the resulting code to a file and/or printing it to standard output.

ENOVA is an open-source service for Large Language Model (LLM) deployment, monitoring, injection, and auto-scaling. It addresses challenges in deploying stable serverless LLM services on GPU clusters with auto-scaling by deconstructing the LLM service execution process and providing configuration recommendations and performance detection. Users can build and deploy LLM with few command lines, recommend optimal computing resources, experience LLM performance, observe operating status, achieve load balancing, and more. ENOVA ensures stable operation, cost-effectiveness, efficiency, and strong scalability of LLM services.

Jina is a tool that allows users to build multimodal AI services and pipelines using cloud-native technologies. It provides a Pythonic experience for serving ML models and transitioning from local deployment to advanced orchestration frameworks like Docker-Compose, Kubernetes, or Jina AI Cloud. Users can build and serve models for any data type and deep learning framework, design high-performance services with easy scaling, serve LLM models while streaming their output, integrate with Docker containers via Executor Hub, and host on CPU/GPU using Jina AI Cloud. Jina also offers advanced orchestration and scaling capabilities, a smooth transition to the cloud, and easy scalability and concurrency features for applications. Users can deploy to their own cloud or system with Kubernetes and Docker Compose integration, and even deploy to JCloud for autoscaling and monitoring.

Vidur is a high-fidelity and extensible LLM inference simulator designed for capacity planning, deployment configuration optimization, testing new research ideas, and studying system performance of models under different workloads and configurations. It supports various models and devices, offers chrome trace exports, and can be set up using mamba, venv, or conda. Users can run the simulator with various parameters and monitor metrics using wandb. Contributions are welcome, subject to a Contributor License Agreement and adherence to the Microsoft Open Source Code of Conduct.

AI System School is a curated list of research in machine learning systems, focusing on ML/DL infra, LLM infra, domain-specific infra, ML/LLM conferences, and general resources. It provides resources such as data processing, training systems, video systems, autoML systems, and more. The repository aims to help users navigate the landscape of AI systems and machine learning infrastructure, offering insights into conferences, surveys, books, videos, courses, and blogs related to the field.