1sec.ai

Tag

#scalability

Every item tagged scalability, newest first.

3 items

toolsAug 8

Accelerate ND-Parallel: A guide to Efficient Multi-GPU Training

The Hugging Face Accelerate library now supports ND-Parallel for efficient multi-GPU training. This feature allows for faster training times and better scalability. You can use it to train large models across multiple GPUs. The guide provides step-by-step instructions for implementation.

Key takeaways
  • Hugging Face Accelerate supports ND-Parallel for multi-GPU training.
  • ND-Parallel enables faster training and better scalability.
  • The feature is useful for training large models across multiple GPUs.
HHugging Face Blog#multi-gpu-training#hugging-face#scalability
modelsJul 10

Building the Hugging Face MCP Server

The Hugging Face team built the Model Catalog Platform (MCP) server to enable fast, scalable model serving. The MCP server handles millions of requests per second, supporting thousands of models and tens of thousands of users. You can deploy and serve models using the Hugging Face Hub API. The MCP server is a key component of Hugging Face's infrastructure, allowing for efficient model management and deployment.

Key takeaways
  • Handles millions of requests per second
  • Supports thousands of models and tens of thousands of users
  • Deploy models using Hugging Face Hub API
HHugging Face Blog#model-serving#scalability#infrastructure
otherSep 19

Rocket Money x Hugging Face: Scaling Volatile ML Models in Production​

Rocket Money partnered with Hugging Face to deploy and manage volatile machine learning models in production. They achieved 99.9% uptime and scaled to handle 1.5M requests per day. The collaboration enabled Rocket Money to efficiently manage complex models and improve customer experience.

Key takeaways
  • 99.9% uptime for volatile ML models
  • 1.5M requests per day
  • managed with Hugging Face
HHugging Face Blog#production-ai#model-management#scalability