InferenceEfficiency

書いてみる

関連タグ

#Gecko (15)
#PaLM2 (23)
#SpeculativeDecoding (1)
#TandemTransformers (1)
#largelanguagemodels (10)
#トークン (3,840)

Tandem Transformers for Inference Efficient LLMs

Ikemen Mas Kot
7か月前