nandish486
nandish486
he have no time to give you a proper answer. hai Wutze give a proper answer don't show your attitude. Please......................
Hi Lirantal, If you have time, so please provide me solutions.
> DirectML can run any LLM on any GPU that supports DX12: > > ``` > if opt.use_dml: > import torch_directml > device = torch_directml.device(torch_directml.default_device()) > else: > device =...
same problem
> @nandish486 There is already some filtering/blocking plugins in the examples directory that you can use as a skeleton for your application. Sir can you show me file? Actually I...
> @nandish486 , I'm glad to hear that you are using daloRADIUS! 😊 > > However, it seems like some _important details_ are still missing. Don't worry, this is something...