bentoml/BentoML

The easiest way to serve AI apps and models - Build Model Inference APIs, Job queues, LLM apps, Multi-model pipelines, and more!

语言：Python · GitHub 星标：8,930 · Fork：1,052

话题：ai-inference · deep-learning · generative-ai · inference-platform · llm · llm-inference · llm-serving · llmops

在 GitHub 上查看原仓库