The DevOpsBeast Blog

Production engineering notes.

Field notes on Kubernetes, GPUs, Linux, and the rest of the production stack, from engineers who run real infrastructure.

LLM Infrastructure··13 min read

Your GPU Finishes a Request and Waits for the Slowest. Continuous Batching Is the Fix.

Static batching pads every request to the length of the longest one in the batch. Short requests finish and their GPU slots sit idle, burning money, until the whole batch drains. Continuous batching schedules at the granularity of a single token instead of a whole request — and it is the single biggest reason vLLM is 5x faster than naive serving. Here is exactly how it works.

Read post
LLM Infrastructure··15 min read

Your HPA Scales LLM Pods on CPU. They're Either Idle or On Fire.

The default Kubernetes autoscaler watches CPU. Your GPU sits at 100% no matter what. So your inference fleet either never scales or scales 90 seconds too late, after the cold start, after the SLO already broke. The signals that actually predict load, the KEDA wiring, and the cold-start tax that makes reactive scaling a trap.

Read post
LLM Infrastructure··16 min read

Your LLM Bill Tripled and Traffic Didn't. Welcome to Prompt Economics.

The unit of cost in an LLM system is the token, and almost nobody is counting them. Output tokens cost 3-5x input. Your context window is 80% dead weight. This is the cost-per-request math, where the tokens actually go, and the levers that bend the curve — in ROI order.

Read post