Primary sourceSimon Willison’s Weblog
View sourceEvent ·Multi-source
LLM Chat Completions Server 0.1a0 发布,本地运行 OpenAI 兼容 API
llm-chat-completions-server 0.1a0 基于 LLM 0.32rc1 的 content-addressable logs 特性构建,支持通过 OpenAI Chat Completions 格式请求多轮对话。用户安装后可通过命令行启动本地服务器(默认端口 9001),暴露所有已安装的 LLM 模型(如 qwen3.5-4b)。该插件由 GPT-5.6 Sol 编写,能自动去重重复消息部分。每个请求可携带完整对话历史,客户端负责维护状态。
Current read
Simon 搞了个小工具,让你在本地用 OpenAI 的 API 格式调用任何 LLM 模型,像 qwen3.5-4b 这种,还能自动去重消息,试试看。
11 sources49° AI heatLast updated 2026/7/30 15:43:16
Evidence
11 sourcesRelated source 1OpenAI
View sourceRelated source 2Greg Brockman
View sourceRelated source 3Geek
View sourceRelated source 4@OpenAIDevs
View sourceRelated source 5LangChain
View sourceRelated source 6Latent.Space
View sourceRelated source 7宝玉
View sourceRelated source 8IT之家
View sourceRelated source 9歸藏(guizang.ai)
View sourceRelated source 10向阳乔木
View sourceConflict check
Dedup data only shows that these sources discuss the same event, not that they agree. There is no structured supporting or refuting evidence yet, so no conflict is inferred automatically.