Completed
Video Overview
Class Central Classrooms beta
YouTube videos curated by Class Central.
Classroom Contents
Speculative Decoding: Techniques for Faster LLM Inference
Automatically move to the next video in the Classroom when playback concludes
- 1 Faster inference with Speculative Decoding
- 2 Video Overview
- 3 How speculative decoding works?
- 4 Naive speculative decoding
- 5 Prompt based n-gram speculation
- 6 Lookahead decoding
- 7 Assisted decoding
- 8 Summary of Decoding Techniques
- 9 Performance Testing
- 10 Summary of Results
- 11 Tips for faster inference