runpod-workers/worker-vllm
A serverless worker template for deploying OpenAI-compatible vLLM-powered LLM inference endpoints on RunPod.
Not currently ranked — collecting fresh signals.
star history
This repository provides a RunPod worker template for serving large language model endpoints using the vLLM inference engine. It enables deploying blazing-fast, OpenAI-compatible LLM endpoints on RunPod serverless infrastructure with minimal configuration. The template supports arbitrary model architectures compatible with vLLM and exposes OpenAI-style chat completions and completions APIs.
Frequently asked
- What is runpod-workers/worker-vllm?
- A serverless worker template for deploying OpenAI-compatible vLLM-powered LLM inference endpoints on RunPod.
- Is worker-vllm open source?
- Yes — runpod-workers/worker-vllm is open source, released under the MIT license.
- What language is worker-vllm written in?
- runpod-workers/worker-vllm is primarily written in Python.
- How popular is worker-vllm?
- runpod-workers/worker-vllm has 455 stars on GitHub.
- Where can I find worker-vllm?
- runpod-workers/worker-vllm is on GitHub at https://github.com/runpod-workers/worker-vllm.