Cross-request KV cache exposure in the GLM-5.3 Workers AI model, and our remediation with SGLang
Cybersecurity Classified by Officially
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.
This is an extract. The publication continues at the source.
Read the original at the source: https://blog.cloudflare.com/kv-cache-exposure-remediation/
Officially imported this from Cloudflare’s own source and shows an extract. If you work there, claiming the profile and verifying the domain lets you choose to show the full text here.
Provenance
- Organization
- Cloudflare — imported from official source
- Official source
- https://blog.cloudflare.com/rss/ RSS
- Imported
- October 26, 2026 22:02
- Versions
- 1 recorded
- Identity
-
01M5X2P6CQYMNAESRJ922DG5J3