SpeculativeDecoding

書いてみる

関連タグ

#Gecko (15)
#InferenceEfficiency (1)
#PaLM2 (23)
#TandemTransformers (1)
#largelanguagemodels (9)
#トークン (3,705)

Tandem Transformers for Inference Efficient LLMs

Ikemen Mas Kot
6か月前