Completed
Quantizing embedding layers
Class Central Classrooms beta
YouTube videos curated by Class Central.
Classroom Contents
Extremely Low-Bit Quantization for Transformers - tinyML Asia 2021
Automatically move to the next video in the Classroom when playback concludes
- 1 Introduction
- 2 Computing system design
- 3 Transformer architecture
- 4 Uniform quantization
- 5 Uniform quantization scheme
- 6 Uniform continuation limits
- 7 Is it still useful
- 8 BCQ
- 9 Example
- 10 Critical problems
- 11 Lookup table
- 12 Transformer structure
- 13 Quantizing embedding layers
- 14 Mixed precision quantization
- 15 Encoder and Decoder
- 16 Retraining
- 17 Quantitation Results
- 18 Latency Improvements
- 19 Quantization
- 20 Q A
- 21 Strategic Partners
