llm-caching

【设计与创意】Optimize LLM costs and latency through KV caching and prompt caching. Use when (1) structuring prompts for cache hits, (2) configuring API cache_control for Anthropic/Cohere/OpenAI/Gemini, (3) setting up self-hosted inference with vLLM/SGLang/Ollama, (4) building agentic workflows with prefix reuse, (5) designing batch processing pipelines, or (6) un…

独立 GitHub 快照 · 自动分类 · 以原作者文档为准