Hugging Face Inference Endpoints

HF Inference Endpoints managed deploy of HF Hub models.

Definition

Inference Endpoints supports text generation (LLMs), text classification, NER, summarization, translation, image classification, object detection, embeddings, ASR (Whisper), TTS. Auto-scaling 0-N replicas. Pay-per-second. Available clouds: AWS (us-east-1, eu-west-1), Azure (eastus, westus2), GCP. Service distinct from Serverless Inference API and HF Inference Providers.

Origin

Hugging Face Inc., founded 2016, Inference Endpoints launched 2022, Series D $235M 2023 $4.5B valuation.

Usage

Standard for managed deployment of HF Hub open-source models. Adopted by Bloomberg, Pfizer, NASA, Mercado Libre.

Related terms

• Hugging Face — plateforme parent.
• Hugging Face Hub — catalogue modèles.
• Together AI — concurrent.