# Concurrency Support #### Concurrency Support Ollama is designed to handle **multiple requests concurrently**, allowing you to serve several clients or processes at once. By default, the Ollama server runs as a long-lived process and accepts parallel HTTP requests over its OpenAI-compatible API endpoints (e.g., `/v1/chat/completions`). Key concurrency features: * Each request spawns its own model evaluation stream * Server manages batching and queuing under the hood for fair scheduling * Safe to send simultaneous requests from different threads, processes, or machines * Built-in load balancing across multiple Ollama instances --- # Agent Instructions: Querying This Documentation If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question. Perform an HTTP GET request on the current page URL with the `ask` query parameter: ``` GET https://docs.scrt.network/secret-network-documentation/secret-ai/sdk/setting-up-your-environment/concurrency-support.md?ask= ``` The question should be specific, self-contained, and written in natural language. The response will contain a direct answer to the question and relevant excerpts and sources from the documentation. Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.