Text Generation Inference (TGI)

Expert guidance for Hugging Face's production LLM inference server.

Triggers

Use this skill when:

• Deploying LLMs in production environments
• Setting up high-throughput model serving
• Configuring quantization for inference optimization
• Working with Hugging Face Text Generation Inference
• Implementing continuous batching or tensor parallelism
• Keywords: tgi, text generation inference, huggingface serving, llm deployment, continuous batching, tensor parallelism

Installation

Docker