Artificial Intelligence
308 views
Quantization
Quick Definition
Reducing model precision from 32-bit to lower bit representations
Full Definition
Reducing model size and computation by representing weights with lower precision numbers like INT8.
Examples
INT8 inference, mixed precision, PTQ
Related Terms
pruning
model-distillation
More Artificial Intelligence Terms
Generative AI
AI systems that create new content
AI Governance
Framework for responsible AI development policies
Neural Architecture Search
Automating the design of optimal neural network architectures
Chain-of-Thought
Technique encouraging AI to show step-by-step reasoning
Bag of Words
Text model representing documents by word frequency counts
In-Context Learning
LLMs learning new tasks from prompt examples without weight updates