TypeLLM 发布：用 JSON Schema 约束解码实现类型化 LLM 输出
Open source meets type-safe AI, with TypeLLM.
TypeLLM 发布，定位为可在一次 API 调用中执行整个工作流的模型，把整条流程写成一份 JSON Schema，并在单一共享上下文上按依赖图执行。它基于 SGLang 将 JSON Schema 转为约束解码，enum 或 boolean 只保留一个打分 token、数字限定位数，并复用缓存前缀，因此字段不会返回枚举外的值。官方称无需改动权重即可从现成 Qwen checkpoint 获得 schema 保证的输出。
查看原帖Chat models return messages. Decision models return decisions. Workflow models execute workflows. TypeLLM introduces the first workflow model. Run an entire workflow in a single API call. Simpler, faster, cheaper. Try it now: https://t.co/GNW18K1iQM https://t.co/YYGne02Fb6
正文
当前显示原文，中文全文译文尚未就绪。
Open source meets type-safe AI, with TypeLLM.
Chat models give you a reply and decision models give you a choice, but TypeLLM is built to run your whole workflow in one API call.
Most production pipelines need something in between: several typed answers, some depending on others, a few that should exist only under certain conditions.
TypeLLM takes that whole shape as one JSON Schema and executes it as a dependency graph over a single shared context.
Typed LLM outputs, built in the open.
You can get schema-guaranteed outputs from a stock Qwen checkpoint without touching its weights.
The guarantee comes from how the requests are built and decoded.
TypeLLM sits on SGLang and turns a JSON Schema into constrained decoding: one scored token for an enum or boolean, bounded digits for numbers, and a dependency graph that reuses cached prefixes.
So a field can’t return a value outside its enum, because the decoder only considers the allowed candidates.