Firehose

Filtered to Companies, tagged “GLM” · clear filters

Browse: People · Companies · Papers · Podcasts · Hacker News · Deep dives

All People Companies Papers Podcasts Hacker News

Browse by tag

artificial intelligence 21 open-weight models 9 agentic coding 5 data integration 4 Vercel 4 machine learning 3

26 OCT 2026 · Cloudflare

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.

Cross-request KV cache SGLang GLM