PyPI page
Home page
Author:
michaelfeil
License:
MIT
Summary:
Infinity is a high-throughput, low-latency REST API for serving text-embeddings, reranking models and clip.
Latest version:
0.0.77
Required dependencies:
huggingface_hub
|
numpy
Optional dependencies:
colpali-engine
|
ctranslate2
|
diskcache
|
einops
|
fastapi
|
onnxruntime-gpu
|
optimum
|
orjson
|
pillow
|
posthog
|
prometheus-fastapi-instrumentator
|
pydantic
|
rich
|
sentence-transformers
|
soundfile
|
tensorrt
|
timm
|
torch
|
torchvision
|
transformers
|
typer
|
uvicorn
Downloads last day:
551
Downloads last week:
8,116
Downloads last month:
37,272