Text Generation Inference
ProductOpen-source server for high-performance text-generation inference, historically used across Hugging Face deployment products.
- Oct 1, 2022
- —
- —
- Yes
- —
- 2
Releases
Jan 16, 2025TGI adds multiple inference backendsFeature update
Text Generation Inference added a multi-backend architecture supporting vLLM and TensorRT-LLM alongside its native backend.
Oct 2022Text Generation Inference releasedSDK release
Hugging Face released Text Generation Inference, a production server optimized for large-language-model generation.

