Cloudflare discloses cross-request KV cache leak on GLM-5.3 in Workers AI
Cloudflare
Cloudflare reported that GLM-5.3 on Workers AI (@cf/zai-org/glm-5.3) returned KV-cache data from other customers' earlier sessions in 155 responses between August 27 and September 9, 2026. A configuration mismatch gave prefill GPUs a 681,280-token KV pool against a 1,048,576-token advertised context, and an SGLang bug in disaggregated prefill/decode mode let over-length requests be replaced with a one-token placeholder while the decode node read stale KV pages. Cloudflare raised the pool to about 2.04 million tokens and the SGLang fixes landed across v0.5.20-v0.5.22; it recommends v0.5.22 or later for all operators.
Why it matters
Disaggregated prefill/decode serving can leak other tenants' context when pool size and context length disagree.
Importance: 4/5
Cross-tenant context exposure in production serving, with a fix that every SGLang operator now has to apply.