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.
What happened
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.
Why it matters
The development may change operating conditions or market expectations around Security. Further confirmation and measurable outcomes matter.
Affected entities
View evidence
1 reports · 1 original report · 1 independent
- Cloudflare SecurityPrimary source · Supports · EN · 100%Cross-request KV cache exposure in the GLM-5.3 Workers AI model, and our remediation with SGLang ↗
Claims
- Cross-request KV cache exposure in the GLM-5.3 Workers AI model, and our remediation with SGLang Observed
Conflicts
No material conflict detected in the available evidence.
Timeline
- First reported
Market move following event
Market reaction is not yet available for this asset and time window.
Score explanation
Confidence · formula confidence-2.1.0
Source trust91
Independent corroboration51
Primary evidence100
Claim consistency82
Extraction confidence82
Attribution quality90
Impact · formula impact-2.1.0
Event magnitude45
Market relevance74
Entity significance42
Market breadth45
Novelty68
Urgency55
Ranking · formula rank-1.0.0
Confidence factor0.9145
Freshness factor0.9997
Breaking bonus0