KV cache leak on Cloudflare Workers AI: how an SGLang bug served other users' data, and how to check your stack
How a KV pool smaller than GLM-5.3's context and an SGLang bug leaked users' data on Workers AI, and how to harden PD serving.
System architecture
Data models, migrations and the decisions that are expensive to reverse.
System architecture articles
DeepInfer explained: how DeepSeek's open-source inference engine serves V4.1 Flash, and what it takes to run it
DeepSeek open-sourced DeepInfer, the engine behind V4.1 Flash: what it includes, what it leaves out, the hardware it needs and how to run it.