Cloudflare has identified a cross-request KV cache exposure issue in the GLM-5.3 Workers AI model, which affected 155 responses to prompts longer than 681,280 tokens. The issue was caused by a misconfiguration of the SGLang inference engine, which resulted in the model generating responses that contained data from other customers' requests. The bug was patched, and the model has been restored with a corrected configuration and patched inference engine. AI summary
Firehose
Filtered to tagged “Cross-request” · clear filters
Browse: People · Companies · Papers · Podcasts · Hacker News · Deep dives
Browse by tag
artificial intelligence 70continual learning 27AI 18open-weight models 15reinforcement learning 14agentic coding 12AI agents 11large language models 9tech 9AI safety 7benchmarks 7finance 7open-source 7robotics 7language models 6machine learning 6Reinforcement learning 6Diffusion models 5game development 5natural language processing 5Agentic AI 4anthropic 4computer vision 4cybersecurity 4data integration 4deep learning 4Recursive self-improvement 4Vercel 4video games 4AI infrastructure 3
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.