Local AI Glossary

What is TGI (Text Generation Inference)?

Source: local-llm.net/glossary

Hugging Face's production-grade inference server for LLMs. TGI supports SafeTensors, GPTQ, and AWQ models with features like continuous batching, tensor parallelism, and token streaming. Commonly used for deploying local AI in production environments.

How TGI (Text Generation Inference) fits in the local AI stack

TGI (Text Generation Inference) is part of the broader local AI ecosystem. See the related guides, comparisons, and tools below to see how it applies in practice.

See also

Related terms