Library / SDK
Inference & ServingRetrieval & Memory
Text Embeddings Inference
1Fast 2serving 3for 4text 5embedding 6models
the six Ws · specification
W1
Who
Maintained by Hugging Face.
W2
What
A fast server for embedding and reranking models.
W3
Where
Self-hosted on CPU or GPU.
W4
When
When serving embeddings at high throughput.
W5
Why
Optimized serving for the embedding half of RAG.
W6
With
Model weights and optional GPUs.
W7
Watch
Company-maintained (Hugging Face); open-source (Apache-2.0), self-hostable. Runs on your hardware; embeddings stay local.
alternatives
works with