michaelfeil/infinity

Infinity is a high-throughput, low-latency serving engine for text-embeddings, reranking models, clip, clap and colpali

57
/ 100
Established

Leverages pluggable inference backends (PyTorch, ONNX/TensorRT, CTranslate2) with dynamic batching and worker-threaded tokenization across NVIDIA CUDA, AMD ROCM, CPU, AWS INF2, and Apple MPS. Exposes an OpenAI-compatible REST API built on FastAPI, enabling drop-in replacement for embedding workflows while supporting multi-model orchestration and quantization (int8/fp8).

2,717 stars. Actively maintained with 1 commit in the last 30 days.

No Package No Dependents
Maintenance 13 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 18 / 25

How are scores calculated?

Stars

2,717

Forks

181

Language

Python

License

MIT

Last pushed

Feb 05, 2026

Commits (30d)

1

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/embeddings/michaelfeil/infinity"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.