Is this method implementable on multi-GPUs?

horseee / LLM-Pruner

[NeurIPS 2023] LLM-Pruner: On the Structural Pruning of Large Language Models. Support Llama-3/3.1, Llama-2, LLaMA, BLOOM, Vicuna, Baichuan, TinyLlama, etc.

https://arxiv.org/abs/2305.11627

Apache License 2.0

880 stars 106 forks source link

Is this method implementable on multi-GPUs? #54

Open LeonCheng0129 opened 8 months ago

BrownTan commented 1 week ago

I also want to know