Application
Retrieval & MemoryInference & Serving
Infinity
1High-throughput 2serving 3engine 4for 5text 6embeddings
the six Ws · specification
W1
Who
Open-source project by Michael Feil.
W2
What
A high-throughput server for embeddings and rerankers.
W3
Where
Self-hosted on CPU or GPU.
W4
When
When serving embedding models at high throughput.
W5
Why
OpenAI-compatible embeddings serving with strong performance.
W6
With
Model weights and optional GPUs.
W7
Watch
Individual-maintained; open-source (MIT), self-hostable. Runs on your hardware; embeddings stay local.