Fastest NLP Performance on Commodity CPUs: Deliver BERT-Large Accuracy at DistilBERT Inference Performance

Fastest NLP Performance on Commodity CPUs: Deliver BERT-Large Accuracy at DistilBERT Inference Performance

Whitepapers

Information

Title
Fastest NLP Performance on Commodity CPUs: Deliver BERT-Large Accuracy at DistilBERT Inference Performance
URL
https://neuralmagic.com/blog/bert-large-prune-once-for-distilbert-inference-performance/

Log in

See all the content and easy-to-use features by logging in or registering!