Press release · Cloudflare
Cross-request KV cache exposure in the GLM-5.3 Workers AI model, and our remediation with SGLang
· Originally published by Cloudflare on blog.cloudflare.com
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.
Read the full release on blog.cloudflare.comUnclaimed newsroom
These releases were collected from Cloudflare's public newsroom (cloudflare.com). Cloudflare hasn't joined E-WIREPRESS. Each release links to the original.