Researchers encode 200+ properties of SGLang inference server, uncover 10 bugs
LingmingZhang · x · 2026-10-31
The team behind runtime verification tested SGLang, one of the most widely used LLM inference servers, by formalizing 200+ properties it must always satisfy — derived from its docs, comments and code — then searching for executions that violate them.
They found 10 issues in total; several are under private disclosure, with the public ones listed in the thread. The work demonstrates a reusable methodology for quality-assuring LLM serving infrastructure.
More from Infra
- AI spending spree deepens free cash flow holes; Microsoft stays positive via $25B bond offering — Kr00ney · 2026-10-31
- Google beams Earth prompt to TPU on orbiting satellite, proving space AI data centers work — ns123abc · 2026-10-31
- Google Cloud spend caps go GA with API, live cost reports and automatic monthly resets — rseroter · 2026-10-31
- Swift 1.5 Flash Next Heretic quants add IQ4_XS and IQ3_S tuned for reverse engineering — jjusko20 · 2026-10-31
- ClickHouse discloses unauthenticated RCE vulnerability CVE-2026-116366, patches available — Hacubu · 2026-10-31
- Count document passes, not tokens: batching questions cuts LLM scoring cost — petrusenko_max · 2026-10-31