TGI (Text Generation Inference)

Hugging Face's high-performance open-source LLM inference server. Serve Llama, Mistral, Falcon, and more with continuous batching and quantization.
Open TGI (Text Generation Inference) →
Tags
LLM inference · Hugging Face · open source · self-hosted LLM · GPU serving · free · 18+ · TGI (Text Generation Inference) · free tools · free ai tools · no cost