TorchServe
Description
TorchServe is an open-source model serving framework for PyTorch models that enables easy deployment, scaling, and management of trained models for inference. It provides features like multi-model serving, REST and gRPC endpoints, metrics and logging integration, model versioning, batching, and GPU support to simplify productionizing ML models.
Statistics
Latest version:
1.3.1.303-master
People using it:
Keys:
Clicks:
Mouse Scrolls:
Time Used:
Average Time Used:
Create a free WhatPulse account to unlock detailed usage statistics and charts.
Loading...
| User |
|---|
TorchServe
Application statistics and information.