ShRajSh comments

Repositories
Issues
Comments

Results 1 comments of


                                            ShRajSh

LoRAX server with 2 GPUs and multiple adapters becomes permanently faster in swapping ONLY after parallel execution of requests.

I face the same issue, while I'm running 1 model with 2 different adapters. As I send sequential requests, the 1st adapter loads and is kept attached to the model,...