[Bug]: Rust frontend chat-template rendering fails with 500 “unknown function: raise_exception” for templates that legally use it (e.g. Qwen
![[Bug]: Rust frontend chat-template rendering fails with 500 "unknown function: raise_exception" for templates that legally use it (e.g. Qwen](https://www.chat-gpts.plus/wp-content/uploads/2026/09/59009-5c4e83a4-768x403.jpg)
当你在 vLLM 0.30.0 的 Rust 前端(Rust frontend)下使用带有 raise_exception(...) 调用的 chat template(例如 Qwen3 系列用于校验 reasoning_effort 的模板)发起请求时,minijinja 渲染器不认识该函数,导致
![[Bug]: Host memory is not reducing after the model is loaded into Intel XPU](https://www.chat-gpts.plus/wp-content/uploads/2026/09/50269-2f2deaf5-768x403.jpg)
![[Bug]: GLM-5.3 reasoning leaks into content when clients pass enable_thinking/thinking=false — parser gates on kwargs the GLM-5.3 template n](https://www.chat-gpts.plus/wp-content/uploads/2026/09/54744-b3553957-768x403.jpg)





![[BUG]: Installation Error - "Anything LLM cannot be closed."](https://www.chat-gpts.plus/wp-content/uploads/2026/09/6516-129ea3ac-768x403.jpg)
![[Bug] Queued PDF loses original media payload when merged with a text follow-up](https://www.chat-gpts.plus/wp-content/uploads/2026/09/19367-7e7c936b-1-768x403.jpg)