Mosec is a high-performance and flexible model-serving framework for building ML model-enabled backend and microservices. It bridges the gap between any machine learning models you just trained and the efficient online service API.

Features

  • Web layer and task coordination built with Rust, which offers blazing speed in addition to efficient CPU utilization powered by async I/O
  • User interface purely in Python, by which users can serve their models in an ML framework-agnostic manner using the same code as they do for offline testing
  • Aggregate requests from different users for batched inference and distribute results back
  • Spawn multiple processes for pipelined stages to handle CPU/GPU/IO mixed workloads
  • Designed to run in the cloud, with the model warmup, graceful shutdown, and Prometheus monitoring metrics, easily managed by Kubernetes or any container orchestration systems
  • Focus on the online serving part, users can pay attention to the model optimization and business logic

Project Samples

Project Activity

See All Activity >

License

Apache License V2.0

Follow Mosec

Mosec Web Site

Other Useful Business Software
One Monitoring Tool for IT, OT and Cloud | Free Trial Icon
One Monitoring Tool for IT, OT and Cloud | Free Trial

Vendor-agnostic monitoring across on-prem servers, cloud platforms and OT devices, all in one dashboard. No more tool sprawl.

Modern infrastructure spans data centers, cloud platforms and factory floors, and every blind spot between them is a risk. PRTG supports SNMP, WMI, SSH and other standard protocols to monitor IT, OT and hybrid environments through one customizable dashboard. Build the views your team needs, from network health to application performance, without switching tools. Try PRTG free for 30 days now.
Try PRTG Free
Rate This Project
Login To Rate This Project

User Reviews

Be the first to post a review of Mosec!

Additional Project Details

Programming Language

Python

Related Categories

Python Large Language Models (LLM), Python LLM Inference Tool

Registered

2023-08-25