Moved section

LLM Inference

The inference material now lives under the Build Log as a grouped public section rather than a page of individual repositories.

LLM inference in build log

01

Serving topology and model routing

02

Latency, throughput, batching, and scheduling

03

KV-cache pressure and inference-time compute

04

GPU economics and AI factory architecture

05

Benchmarking, reliability, and observability