---
title: "Comment by Yunus Emre Vurgun on \"Deploying AI Workflows on Cloud Run: Latency, Cold Starts, and Scaling\" | Hashnode"
description: "One small addition to the warming endpoint: since /warm makes a real LLM call, it's worth excluding it from the request-count and latency dashboards (or tagging"
url: "https://hashnode.com/posts/deploying-ai-workflows-on-cloud-run-latency-cold-starts-and-scaling/6ac7e695eed20210cedb42bf/comment/6ad08fc31ce6f3599dfd3f31"
---

[Discussion](https://hashnode.com/posts/deploying-ai-workflows-on-cloud-run-latency-cold-starts-and-scaling/6ac7e695eed20210cedb42bf)

Comment [Deploying AI Workflows on Cloud Run: Latency, Cold Starts, and Scaling](https://hashnode.com/posts/deploying-ai-workflows-on-cloud-run-latency-cold-starts-and-scaling/6ac7e695eed20210cedb42bf)

[Yunus Emre Vurgun](https://hashnode.com/@yunusemrevurgun)

[Oct 15](https://hashnode.com/posts/deploying-ai-workflows-on-cloud-run-latency-cold-starts-and-scaling/6ac7e695eed20210cedb42bf/comment/6ad08fc31ce6f3599dfd3f31)

One small addition to the warming endpoint: since /warm makes a real LLM call, it's worth excluding it from the request-count and latency dashboards (or tagging it), otherwise post-deploy warmups skew the p50/p95 you're using to tune min\_instances. Also, Cloud Run's startup CPU boost pairs well with this: it shortens the 2–5s import/pool init for the cold starts that still happen after a scale-to-zero, without paying for an extra always-on instance.
