Inference

Multi-container application definition format

CoreWeave Inference: CoreWeave Documentation Copy MCP Server Copy MCP Server Learn how to deploy, manage, and observe your workloads on CoreWeave.

CoreWeave Kubernetes Service (CKS): CoreWeave Documentation Copy MCP Server Copy MCP Server Learn how to deploy, manage, and observe your workloads on CoreWeave.

CoreWeave Managed Services: Build AI agents, applications, and models Install W&B MCP Develop AI models and ship LLM applications with the W&B platform for experiment tracking, evaluation, and observability.

CoreWeave Networking: CoreWeave Documentation Copy MCP Server Copy MCP Server Learn how to deploy, manage, and observe your workloads on CoreWeave.

CoreWeave Sandbox: CoreWeave Documentation Copy MCP Server Copy MCP Server Learn how to deploy, manage, and observe your workloads on CoreWeave.

CoreWeave Storage: CoreWeave Documentation Copy MCP Server Copy MCP Server Learn how to deploy, manage, and observe your workloads on CoreWeave.

Docker Engine's image building feature and ecosystem for packaging and shipping code.

Docker command-line interface for container management

Open-source container runtime for Linux, also known as Docker CE.

RESTful API for interacting with the Docker daemon, accessed by an HTTP client such as wget or curl.

Platform for building, training, optimizing, and deploying ML models on edge devices from microcontrollers to GPUs/TPUs.

Web-based platform for building, training, and deploying ML models to edge devices.

Reference glossary defining Elastic product terminology and concepts.

Official Python client for Elasticsearch with pip install support.

FastEmbed: Develop Deploy Ecosystem Learn API Reference Search Log in Start Free Search Develop Deploy Ecosystem Learn API Reference Getting Started Overview What is Qdrant?

Run models directly in your own Python process.

Run LLM inference at maximum throughput This example demonstrates some techniques for running LLM inference at the highest possible throughput on Modal.

ONNX Runtime is a cross-platform inference engine for ONNX models, with APIs in Python, C++, C#, Java, and JavaScript.

Managed vector database for AI applications with integrated embedding, search, and reranking.

pyVespa: Vespa Documentation | Vespa: The AI search platform Vespa basics Deploy an application Vespa applications Schemas Writing Querying Ranking Operations What's more Learn more Vespa overview Getting help from LLMs Features Tutorials and use cases Frequently asked questions Glossary Releases Tenants, apps and instances Migrating to Vespa Cloud Migrating from ElasticSearch About this documentation Contributing to Vespa Applications and components Developer guide IDE support Deployment .vespa

Qdrant: Develop Deploy Ecosystem Learn API Reference Search Log in Start Free Search Develop Deploy Ecosystem Learn API Reference Getting Started Overview What is Qdrant?

Qdrant Cloud: Develop Deploy Ecosystem Learn API Reference Search Log in Start Free Search Develop Deploy Ecosystem Learn API Reference Getting Started Overview What is Qdrant?

Qdrant Edge: Develop Deploy Ecosystem Learn API Reference Search Log in Start Free Search Develop Deploy Ecosystem Learn API Reference Getting Started Overview What is Qdrant?

Qdrant MCP Server: Develop Deploy Ecosystem Learn API Reference Search Log in Start Free Search Develop Deploy Ecosystem Learn API Reference Getting Started Overview What is Qdrant?

Qdrant Web UI: Develop Deploy Ecosystem Learn API Reference Search Log in Start Free Search Develop Deploy Ecosystem Learn API Reference Getting Started Overview What is Qdrant?

Roboflow: For the complete documentation index, see llms.txt .

Roboflow Agents: For the complete documentation index, see llms.txt .

Manage Roboflow plans, payment details, and credit-based workspace spending.

Roboflow CLI: For the complete documentation index, see llms.txt .

Roboflow Datasets: For the complete documentation index, see llms.txt .

Roboflow Deployments: For the complete documentation index, see llms.txt .

Install the CLI and manage your projects from the terminal.

Script uploads, training, and inference from Python.

Authenticate, call any endpoint, and poll async tasks.

SUNK: CoreWeave Documentation Copy MCP Server Copy MCP Server Learn how to deploy, manage, and observe your workloads on CoreWeave.

tRPC: tRPC Introduction Version: 11.x On this page End-to-end typesafe APIs made easy Introduction ​ tRPC lets you build & consume fully typesafe APIs without schemas or code generation.

Unsloth is an open-source library for fine-tuning LLMs with 2x faster training and 70% less memory usage.

Vespa: Vespa Documentation | Vespa: The AI search platform Vespa basics Deploy an application Vespa applications Schemas Writing Querying Ranking Operations What's more Learn more Vespa overview Getting help from LLMs Features Tutorials and use cases Frequently asked questions Glossary Releases Tenants, apps and instances Migrating to Vespa Cloud Migrating from ElasticSearch About this documentation Contributing to Vespa Applications and components Developer guide IDE support Deployment .vespaig

Vespa CLI: Vespa Documentation | Vespa: The AI search platform Vespa basics Deploy an application Vespa applications Schemas Writing Querying Ranking Operations What's more Learn more Vespa overview Getting help from LLMs Features Tutorials and use cases Frequently asked questions Glossary Releases Tenants, apps and instances Migrating to Vespa Cloud Migrating from ElasticSearch About this documentation Contributing to Vespa Applications and components Developer guide IDE support Deployment .ves

Vespa Cloud: Vespa Documentation | Vespa: The AI search platform Vespa basics Deploy an application Vespa applications Schemas Writing Querying Ranking Operations What's more Learn more Vespa overview Getting help from LLMs Features Tutorials and use cases Frequently asked questions Glossary Releases Tenants, apps and instances Migrating to Vespa Cloud Migrating from ElasticSearch About this documentation Contributing to Vespa Applications and components Developer guide IDE support Deployment .v

Vespa Java Feed Client: Vespa Documentation | Vespa: The AI search platform Vespa basics Deploy an application Vespa applications Schemas Writing Querying Ranking Operations What's more Learn more Vespa overview Getting help from LLMs Features Tutorials and use cases Frequently asked questions Glossary Releases Tenants, apps and instances Migrating to Vespa Cloud Migrating from ElasticSearch About this documentation Contributing to Vespa Applications and components Developer guide IDE support De

Command line interface for logging in, running jobs, executing sweeps, and managing artifacts.

Programmatic access to runs, projects, artifacts, reports, teams, and related resources.

Core Python library for experiment tracking, data types, global functions, automations, and custom charts.

Python SDK for machine learning experiment tracking and model management.

Self-hosted and cloud deployment of Weights & Biases experiment tracking platform.

Python client for Weave tracing, evaluations, and trace server integration.

Python and TypeScript libraries for tracing, evaluating, and improving LLM and agent applications.

Weights & Biases MCP: W&B Weave Install W&B MCP Track, test, and improve language model apps with W&B Weave Install W&B MCP W&B Weave is an observability and evaluation platform that helps you track, evaluate, and improve your agents and LLM applications.