Understanding and Overcoming the Challenges of Efficient Transformer Quantization
31249Knowledge Triples
| Source Entity | Relationship | Target Entity |
|---|---|---|
|
Post Training Quantization
Method |
evaluatedIn |
GLUEBenchmark
Material |
|
Quantization
Method |
achieves |
Memory Savings
Metric |
|
Quantization
Method |
isBasedOn |
Post Training Quantization
Method |
|
Quantization
Method |
isBasedOn |
Quantization Aware Training
Method |
|
Quantization Aware Training
Method |
evaluatedIn |
GLUEBenchmark
Material |
|
Transformer Architectures
Method |
explores |
Quantization
Method |