Search Results for "runtime" - Page 3
Sort By:
Showing 73 open source projects for "runtime"
View related business solutions-
MongoDB Atlas runs apps anywhereMongoDB Atlas gives you the freedom to build and run modern applications anywhere—across AWS, Azure, and Google Cloud. With global availability in over 115 regions, Atlas lets you deploy close to your users, meet compliance needs, and scale with confidence across any geography.
-
Build Agents and Models on One PlatformGemini Enterprise Agent Platform is Google Cloud's comprehensive platform for developers to build, scale, govern, and optimize agents and models. Choose from Google's most advanced models and third-party models like Anthropic's Claude Model Family.
-
1
Z80-μLM
Z80-μLM is a 2-bit quantized language model
...The project sits at the intersection of machine learning and systems constraints, showing how model architecture, quantization, and inference code generation can be adapted to extreme memory and compute limits. It also functions as an educational reference for how to reduce inference to operations that fit an old-school instruction set and runtime environment. -
2
Preswald
Python tool for browser-based interactive data apps in one file
...It packages application logic, data processing, and user interface components into a single self-contained output, enabling easy sharing and deployment without requiring local dependencies. Preswald leverages a WebAssembly runtime along with technologies like Pyodide and DuckDB to execute Python code directly in the browser environment. This approach allows developers to create dashboards, reports, notebooks, and data tools that are portable, fast, and capable of running offline. Preswald emphasizes a code-first workflow where users define applications entirely in Python while using built-in UI components such as tables, charts, and forms. ... -
3
CAG
Cache-Augmented Generation: A Simple, Efficient Alternative to RAG
...CAG proposes a different approach by preloading relevant knowledge into the model’s context window and precomputing the model’s key-value cache before queries are processed. This strategy allows the model to generate responses using the cached context directly, eliminating the need for repeated retrieval operations during runtime. As a result, the approach can significantly reduce latency and simplify system architecture compared with traditional RAG pipelines. The framework is particularly effective when the knowledge base is limited enough to fit within the extended context window of modern language models. -
4
tf2onnx
Convert TensorFlow, Keras, Tensorflow.js and Tflite models to ONNX
tf2onnx converts TensorFlow (tf-1.x or tf-2.x), keras, tensorflow.js and tflite models to ONNX via command line or python API. Note: tensorflow.js support was just added. While we tested it with many tfjs models from tfhub, it should be considered experimental. TensorFlow has many more ops than ONNX and occasionally mapping a model to ONNX creates issues. tf2onnx will use the ONNX version installed on your system and installs the latest ONNX version if none is found. We support and test ONNX... -
Cut Data Warehouse Costs by 54%BigQuery delivers 54% lower TCO with exabyte scale and flexible pricing. Free migration tools handle the SQL translation automatically.
-
5
NVIDIA NeMo Agent Toolkit
Library for efficiently connecting and optimizing teams of AI agents
NVIDIA NeMo Agent Toolkit is an open-source framework designed to build, optimize, and manage AI agents across different development ecosystems. It provides enterprise-grade tools for improving agent performance, reliability, and observability throughout the development lifecycle. The toolkit integrates with popular agent frameworks such as LangChain, LlamaIndex, CrewAI, Microsoft Semantic Kernel, and Google ADK. Developers can monitor agent execution, trace workflows, and analyze... -
6
AutoAgent
AutoAgent: Fully-Automated and Zero-Code LLM Agent Framework
AutoAgent is a fully automated, zero-code LLM agent framework that lets users create agents and workflows using natural language instead of manual coding and configuration. It is structured around modes that cover both “use” and “build” scenarios: a user mode for running a ready-made multi-agent research assistant, plus editors for creating individual agents or multi-agent workflows from conversational requirements. The framework emphasizes self-managing workflow generation, where it can... -
7
Seldon Core
An MLOps framework to package, deploy, monitor and manage models
The de facto standard open-source platform for rapidly deploying machine learning models on Kubernetes. Seldon Core, our open-source framework, makes it easier and faster to deploy your machine learning models and experiments at scale on Kubernetes. Seldon Core serves models built in any open-source or commercial model building framework. You can make use of powerful Kubernetes features like custom resource definitions to manage model graphs. And then connect your continuous integration and... -
8
SageMaker Training Toolkit
Train machine learning models within Docker containers
...To train a model, you can include your training script and dependencies in a Docker container that runs your training code. A container provides an effectively isolated environment, ensuring a consistent runtime and reliable training process. The SageMaker Training Toolkit can be easily added to any Docker container, making it compatible with SageMaker for training models. If you use a prebuilt SageMaker Docker image for training, this library may already be included. Write a training script (eg. train.py). Define a container with a Dockerfile that includes the training script and any dependencies. -
9
Matcha-TTS
A fast TTS architecture with conditional flow matching
Matcha-TTS is a non-autoregressive neural text-to-speech architecture that uses conditional flow matching to generate speech quickly while maintaining natural quality. It models speech as an ODE-based generative process, and conditional flow matching lets it reach high-quality audio in only a few synthesis steps, which greatly reduces latency compared to score-matching diffusion approaches. The model is fully probabilistic, so it can generate diverse realizations of the same text while still... -
Fully Managed MySQL, PostgreSQL, and SQL ServerCloud SQL handles your database ops end to end, so you can focus on your app.
-
10
mcp-use
A solution to build and deploy MCP agents and applications
...Developers can create custom agents (via MCPAgent) that dynamically select the most appropriate server for each task using configurable pipelines or a built-in server manager. It simplifies authentication, access control, audit logging, observability, sandboxed runtime environments, and deployment workflows, whether self-hosted or managed, making MCP development production-ready. With integrations for popular frameworks like LangChain (Python) and LangChain.js (TypeScript), mcp-use accelerates the creation of tool-enabled AI agents. -
11
Agent Payments Protocol (AP2)
Building a Secure and Interoperable Future for AI-Driven Payments
...It includes “types” definitions (the core message and object schema) and example agent implementations to demonstrate the mechanics of agent-to-agent and agent-to-server interactions. The design emphasizes flexibility: although their samples use a particular Agent Development Kit (ADK) or runtime, the protocol is intended to be independent of those choices. -
12
chatd
Chat with your documents using local AI
...The software focuses on privacy and security by ensuring that all document processing and inference occur entirely on the user’s computer without sending data to external cloud services. It includes a built-in integration with the Ollama runtime, which provides a cross-platform environment for running large language models locally. The application typically runs models such as Mistral-7B and allows users to load and analyze documents while asking questions in natural language. Unlike many document-chat tools that require manual installation of model servers, chatd packages the model runner with the application so that users can start interacting with documents immediately after launching the program. -
13
MMDeploy
OpenMMLab Model Deployment Framework
...All kinds of modules in the SDK can be extended, such as Transform for image processing, Net for Neural Network inference, Module for postprocessing and so on. Install and build your target backend. ONNX Runtime is a cross-platform inference and training accelerator compatible with many popular ML/DNN frameworks. Please read getting_started for the basic usage of MMDeploy. -
14
CLIP-as-service
Embed images and sentences into fixed-length vectors
CLIP-as-service is a low-latency high-scalability service for embedding images and text. It can be easily integrated as a microservice into neural search solutions. Serve CLIP models with TensorRT, ONNX runtime and PyTorch w/o JIT with 800QPS[*]. Non-blocking duplex streaming on requests and responses, designed for large data and long-running tasks. Horizontally scale up and down multiple CLIP models on single GPU, with automatic load balancing. Easy-to-use. No learning curve, minimalist design on client and server. Intuitive and consistent API for image and sentence embedding. ... -
15
RWKV
RNN with great LLM performance
...The repository includes training code, model notes, research material, and references to current RWKV weights. Its main value is providing the foundation for experimenting with efficient large language models that combine transformer-like scalability with RNN-like runtime behavior. -
16
pipeless
A computer vision framework to create and deploy apps in minutes
...You can easily use industry-standard models, such as YOLO, or load your custom model in one of the supported inference runtimes. Pipeless ships some of the most popular inference runtimes, such as the ONNX Runtime, allowing you to run inference with high performance on CPU or GPU out-of-the-box. You can deploy your Pipeless application with a single command to edge and IoT devices or the cloud. -
17
SageMaker Inference Toolkit
Serve machine learning models within a Docker container
...Once you have a trained model, you can include it in a Docker container that runs your inference code. A container provides an effectively isolated environment, ensuring a consistent runtime regardless of where the container is deployed. Containerizing your model and code enables fast and reliable deployment of your model. The SageMaker Inference Toolkit implements a model serving stack and can be easily added to any Docker container, making it deployable to SageMaker. This library's serving stack is built on Multi Model Server, and it can serve your own models or those you trained on SageMaker using machine learning frameworks with native SageMaker support. -
18
langchain-prefect
Tools for using Langchain with Prefect
...Prefect is built to help data people build, run, and observe event-driven workflows wherever they want. It provides a framework for creating deployments on a whole slew of runtime environments (from Lambda to Kubernetes), and is cloud agnostic (best supports AWS, GCP, Azure). For this reason, it could be a great fit for observing apps that use LLMs. RecordLLMCalls is a ContextDecorator that can be used to track LLM calls made by Langchain LLMs as Prefect flows. Run several LLM calls via langchain agent as Prefect subflows. -
19
Hugging Face Transformer
CPU/GPU inference server for Hugging Face transformer models
...Most tutorials on Transformer deployment in production are built over Pytorch and FastAPI. Both are great tools but not very performant in inference. Then, if you spend some time, you can build something over ONNX Runtime and Triton inference server. You will usually get from 2X to 4X faster inference compared to vanilla Pytorch. It's cool! However, if you want the best in class performances on GPU, there is only a single possible combination: Nvidia TensorRT and Triton. You will usually get 5X faster inference compared to vanilla Pytorch. -
20
CLIP Guided Diffusion
A CLI tool/python module for generating images from text
...Non-square Generations (experimental) Generate portrait or landscape images by specifying a number to offset the width and/or height. Uses fewer timesteps over the same diffusion schedule. Sacrifices accuracy/alignment for quicker runtime. options: - 25, 50, 150, 250, 500, 1000, ddim25,ddim50,ddim150, ddim250,ddim500,ddim1000 (default: 1000) Prepending a number with ddim will use the ddim scheduler. e.g. ddim25 will use the 25 timstep ddim scheduler. This method may be better at shorter timestep_respacing values. Multiple prompts can be specified with the | character. ... -
21
nlp-tutorial
Natural Language Processing Tutorial for Deep Learning Researchers
...Later examples implement the Transformer and BERT for translation, classification, and masked-token tasks. Paper links and Google Colab notebooks connect each implementation with its research background and an accessible runtime. -
22
Tangent
Source-to-source debuggable derivatives in pure Python
Existing libraries implement automatic differentiation by tracing a program's execution (at runtime, like PyTorch) or by staging out a dynamic data-flow graph and then differentiating the graph (ahead-of-time, like TensorFlow). In contrast, Tangent performs ahead-of-time autodiff on the Python source code itself, and produces Python source code as its output. Tangent fills a unique location in the space of machine learning tools. -
23
Yann is Yet Another Neural Network. Yann is a library to create fast neural networks. It is also a GUI to easily create, edit, train, execute and investigate networks. Multiple topologies, runtime properties and ensemble learning are supported.