fastDeploy
Deploy DL/ ML inference pipelines with minimal extra code.
Installation:
pip install --upgrade fastdeployUsage:
# Invoke fastdeploy
fastdeploy --help
# or
python -m fastdeploy --help
# Start prediction "loop" for recipe "echo_json"
fastdeploy --recipe ./echo_json --mode loop
# Start rest apis for recipe "echo_json"
fastdeploy --recipe ./echo_json --mode rest
# Auto genereate dockerfile and build docker image. --base is docker base
fastdeploy --recipe ./recipes/echo_json/ \
--mode build_rest --base python:3.6-slim
# fastdeploy_echo_json built!
# Run docker image
docker run -it -p8080:8080 fastdeploy_echo_json
fastDeploy monitor
- available on localhost:8080 (or --port)
- https://github.com/notAI-tech/fastDeploy/blob/master/recipe.md Writing a recipe for your prediction script
- https://github.com/notAI-tech/fastDeploy/blob/master/inference.md cURL and Python inference commands.
