vllm-project/production-stack
A Kubernetes-native reference stack for deploying and scaling vLLM LLM inference across distributed clusters.
Not currently ranked — collecting fresh signals.
star history
The vLLM Production Stack provides a reference implementation for deploying vLLM inference engines at scale in production. It enables scaling from single instances to distributed Kubernetes deployments without changing application code. The stack includes web-based monitoring dashboards, request routing for load distribution, and KV cache offloading to optimize inference performance across cluster-wide deployments.
Frequently asked
- What is vllm-project/production-stack?
- A Kubernetes-native reference stack for deploying and scaling vLLM LLM inference across distributed clusters.
- Is production-stack open source?
- Yes — vllm-project/production-stack is open source, released under the Apache-2.0 license.
- What language is production-stack written in?
- vllm-project/production-stack is primarily written in Python.
- How popular is production-stack?
- vllm-project/production-stack has 2.5k stars on GitHub.
- Where can I find production-stack?
- vllm-project/production-stack is on GitHub at https://github.com/vllm-project/production-stack.