AI Gateway on PlumePHPhttps://plumephp.com/tags/ai-gateway/Recent content in AI Gateway on PlumePHPHugozh-CNSat, 15 Jun 2024 00:00:00 +0800Cloudflare Workers AI 高级实战：自定义模型部署、批量推理与 AI Gateway 缓存策略https://plumephp.com/cloudflare-workers-ai-advanced/Sat, 15 Jun 2024 00:00:00 +0800https://plumephp.com/cloudflare-workers-ai-advanced/Workers AI 高级实战：模型量化与推理延迟优化、批量请求合并、AI Gateway 缓存策略（TTL/语义缓存）、多模型路由与故障转移、自定义模型部署（ONNX/TensorFlow.js），含 Workers AI Catalog 全矩阵对比。