Simple, but Powerful.
Help wanted. Translation, rap lyrics, all wanted. Feel free to create an issue.
Pinferencia tries to be the simplest machine learning inference server ever!
Three extra lines and your model goes online.
Serving a model with REST API has never been so easy.
If you want to
- find a simple but robust way to serve your model
- write minimal codes while maintain controls over you service
- avoid any heavy-weight solutions
- compatible with other tools/platforms
You're at the right place.
Pinferencia features include:
- Fast to code, fast to go alive. Minimal codes needed, minimal transformation needed. Just based on what you have.
- 100% Test Coverage: Both statement and branch coverages, no kidding. Have you ever known any model serving tool so seriously tested?
- Easy to use, easy to understand.
- Automatic API documentation page. All API explained in details with online try-out feature.
- Serve any model, even a single function can be served.
- Support Kserve API, compatible with Kubeflow, TF Serving, Triton and TorchServe. There is no pain switching to or from them, and Pinferencia is much faster for prototyping!
pip install "pinferencia[uvicorn]"Serve Any Model
from pinferencia import Server
class MyModel:
def predict(self, data):
return sum(data)
model = MyModel()
service = Server()
service.register(model_name="mymodel", model=model, entrypoint="predict")Just run:
uvicorn app:service --reload
Hooray, your service is alive. Go to http://127.0.0.1:8000/ and have fun.
Any Deep Learning Models? Just as easy. Simple train or load your model, and register it with the service. Go alive immediately.
Hugging Face
Details: HuggingFace Pipeline - Vision
from transformers import pipeline
from pinferencia import Server
vision_classifier = pipeline(task="image-classification")
def predict(data):
return vision_classifier(images=data)
service = Server()
service.register(model_name="vision", model=predict)Pytorch
import torch
from pinferencia import Server
# train your models
model = "..."
# or load your models (1)
# from state_dict
model = TheModelClass(*args, **kwargs)
model.load_state_dict(torch.load(PATH))
# entire model
model = torch.load(PATH)
# torchscript
model = torch.jit.load('model_scripted.pt')
model.eval()
service = Server()
service.register(model_name="mymodel", model=model)Tensorflow
import tensorflow as tf
from pinferencia import Server
# train your models
model = "..."
# or load your models (1)
# saved_model
model = tf.keras.models.load_model('saved_model/model')
# HDF5
model = tf.keras.models.load_model('model.h5')
# from weights
model = create_model()
model.load_weights('./checkpoints/my_checkpoint')
loss, acc = model.evaluate(test_images, test_labels, verbose=2)
service = Server()
service.register(model_name="mymodel", model=model, entrypoint="predict")Any model of any framework will just work the same way. Now run uvicorn app:service --reload and enjoy!
If you'd like to contribute, details are here