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.
Every article tagged #sglang, across topics.
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.
Mistral Large 4 weights are out: what the 1T MoE needs in GPU memory, what the licence allows, and the vLLM and SGLang commands to serve it.