高速推論

書いてみる

関連タグ

#モデル (14,779)
#CS (3,393)
#GQA (1)
#LLM (6,208)
#MMLU (9)
#TriForce (1)

TriForce: Lossless Acceleration of Long Sequence Generation with Hierarchical Speculative Decoding

Ikemen Mas Kot
6か月前

Dynamic Memory Compression: Retrofitting LLMs for Accelerated Inference

Ikemen Mas Kot
6か月前