Gemini 流 式 输出

Yet Another Gemini Server - A gemini protocol server

Local AI workbench for embeddings, summarization, and OpenAI Agent SDK–compatible workflows. Supports Gemma models, GPT-OSS tool-calling, hardware acceleration, caching, and rate limiting, plus cloud-offloaded, persona-driven summarization through Gemini. (This is a mirror project)

A build machine for C/C++ x86_64 and ARM targets.

An interactive React application to explore and visualize Gemini chat conversations with advanced rendering, sidebar navigation, and local JSON file loading. (This is a mirror project)

Gemini gateway. For low-latency trading, including HFT, market making and arbitrage.

AI-powered GitLab automation using Sequential Thinking, Gemini Flash 2.0, and MCP servers - automated issue tracking, branch management, and intelligent workflows

sample app repo

新智元报道 编辑：桃子 好困 【新智元导读】卷疯了！世界最快的大模型Groq一夜之间爆火，能够每秒输出近500个token。如此神速的响应，背后全凭自研的LPU。 一觉醒来，每秒能输出500个token的Groq模型刷屏全网。 堪称是「世界上速度最快的LLM」！ 相比之下，ChatGPT-3.5每秒