Zero-Copy Model Loading with Ray and PyTorch for Efficient Deep Learning Inference

Zero-Copy Model Loading with Ray and PyTorch for Efficient Deep Learning Inference

Anyscale via YouTube Direct link

Benchmark implementation

8 of 9

8 of 9

Benchmark implementation

Class Central Classrooms beta

YouTube videos curated by Class Central.

Classroom Contents

Zero-Copy Model Loading with Ray and PyTorch for Efficient Deep Learning Inference

Automatically move to the next video in the Classroom when playback concludes

  1. 1 Intro
  2. 2 Model Serving 101
  3. 3 Loading PyTorch tensors without copying data
  4. 4 Model inference on Ray using stateless tasks
  5. 5 Summary: Model inference with zero-copy loading
  6. 6 A simple benchmark
  7. 7 Pre- and post-processing with Ray Serve
  8. 8 Benchmark implementation
  9. 9 Benchmark Results

Never Stop Learning.

Get personalized course recommendations, track subjects and courses with reminders, and more.

Someone learning on their laptop while sitting on the floor.