search

randaller / llama-chat

Chat with Meta's LLaMA models at home made easy
GNU General Public License v3.0
834 stars 118 forks source link

It's too slow, how run 30B on 4 GPUs interactively #6

Closed zhongtao93 closed 1 year ago

tkone2018 commented 1 year ago

@zhongtao93 hello, can you solve it?

zhongtao93 commented 1 year ago

No~

zhongtao93 commented 1 year ago

@zhongtao93 hello, can you solve it? The expert has solved this problem https://github.com/facebookresearch/llama/issues/162#issuecomment-1464996569