vLLM Production Stack GitHub repository

Fields

id

sources/niche-vllm-production-stack-repo

URL

https://github.com/vllm-project/production-stack

Publisher

vLLM project

Kind

repo

Accessed

2026-10-03

notes

vLLM Production Stack README: the reference K8s-native deployment for vLLM, covering request routing and KV-cache offloading via LMCache, Helm-based install, cloud tutorials for AWS/GCP/Lambda Labs/Azure, and multi-model launches. First released 2025-01-21. API metadata 2026-10-03: last push 2026-10-02, latest release vllm-stack-0.1.13 (2026-09-29) - still on a 0.1.x version line, which is the maturity signal. Apache-2.0, 322 open issues, 2654 stars.

Notes

vLLM Production Stack README: the reference K8s-native deployment for vLLM, covering request routing and KV-cache offloading via LMCache, Helm-based install, cloud tutorials for AWS/GCP/Lambda Labs/Azure, and multi-model launches. First released 2025-01-21. API metadata 2026-10-03: last push 2026-10-02, latest release vllm-stack-0.1.13 (2026-09-29) - still on a 0.1.x version line, which is the maturity signal. Apache-2.0, 322 open issues, 2654 stars.

Cross-references

This record references no other records.