Cross-request KV cache exposure in the GLM-5.3 Workers AI model, and our remediation with SGLang
// AI summary
Cloudflare addressed a configuration mismatch in GLM-5.3 on Workers AI that triggered an SGLang bug, exposing KV cache pages across different requests.
// from the source
A configuration mismatch in GLM 5.3 on Workers AI triggered an SGLang bug that exposed KV cache pages across requests. Here is how we addressed the issue.