Congratulations for adding LLaVA support starting with version 0.11.1.
It works very well!
Still, clip model is very slow.
I have Cuda12 and llava-mistral model is using GPU, as expected, but the clip model is not, instead is using the CPU.


NativeLibraryConfig.Instance
.WithCuda(true)
.WithLogs(true)
.WithAvx(NativeLibraryConfig.AvxLevel.Avx512);
Should the clip model run on GPU as well?
Congratulations for adding LLaVA support starting with version 0.11.1.
It works very well!
Still, clip model is very slow.
I have Cuda12 and llava-mistral model is using GPU, as expected, but the clip model is not, instead is using the CPU.
NativeLibraryConfig.Instance
.WithCuda(true)
.WithLogs(true)
.WithAvx(NativeLibraryConfig.AvxLevel.Avx512);
Should the clip model run on GPU as well?