Turn any idea, plan, or codebase into a beautiful interactive diagram. An agent skill for Claude Code, Codex, and more.
Repository dossier
vllm-project/recipes
Common recipes to run vLLM
Brief / README 摘要
查看原文This repo intends to host community maintained common recipes to run vLLM answering the question: *How do I run model X on hardware Y for task Z?** DeepSeek-OCR DeepSeek-V3.1 DeepSeek-V3, DeepSeek-R1 DeepSeek-V3.2-Exp DeepSeek-V3.2 GLM-5.1, GLM-5 Glyph GLM-4.7-Flash, GLM-4.7, GLM-4.6, GLM-4.5, GLM-4.5-Air GLM-4.5V, GLM-4.6V Llama4-Scout Llama3.3-70B Llama3.1 MiniMax-M2.7, MiniMax-M2.5, MiniMax-M2.1, MiniMax-M2 Ministral-3-Instruct Ministral-3-Reasoning Mistral-Large-3-Instruct Kimi-K2.5 Kimi-K2 Kimi-K2-Think Kimi-Linear Nemotron-3-Nano-30B-A3B Nemotron-Nano-12B-v2-VL Qwen3 Qwen3-ASR Qwen3-VL Q…
相关推荐
Agent skills that give coding agents taste: art direction, reference images and a browser check instead of generic AI pages
Production-grade engineering skills for AI coding agents.
Java 面试 & 后端通用面试指南,覆盖计算机基础、数据库、分布式、高并发、系统设计与 AI 应用开发
Makes your AI agent think like the laziest senior dev in the room. The best code is the code you never wrote.
The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.