Codú
‹ Back to feed

// Link · 26 October 2026

Cross-request KV cache exposure in the GLM-5.3 Workers AI model, and our remediation with SGLang

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.

Cloudflare Blog
@cloudflare-blog · blog.cloudflare.com
blog.cloudflare.com
Visit Link at blog.cloudflare.com
Cloudflare Blog@cloudflare-blog

Discussion 0

Loading

Got something to say?

or to join the conversation.

Learn to build with AI and grow with people doing the same — it's free.