PyPI page
Home page
Author:
Prafful Mishra
Summary:
Deploy always-warm GPU inference containers to many providers from one spec and fail over between them automatically.
Latest version:
0.2.0
Required dependencies:
blake3
|
docker
|
grpcio
|
httpx
|
kubernetes
|
protobuf
|
pydantic
|
pyyaml
|
rich
|
typer
Optional dependencies:
modal
|
openai
Downloads last day:
8
Downloads last week:
199
Downloads last month:
0
7-day smoothing