LLava_shared.dll in LLamaSharp.Backend.Cuda12 is for CPU only

[IntptrMax]

The llava_shared.dll in LLamaSharp.Backend.Cuda12 is only 850KB, the file size is much smaller than llava_shared.dll with cuda. It will take about 126000+ ms to embding an image. Take it to llava_shared.dll from llama.cpp release 2214, image embding time will be no more than 1000 ms. Will this can be updated in next LLamaSharp release?

[Current]

[Dll replaced]

[SanftMonster]

That's unexpected, we will add a patch release ASAP. @martindevans Could you please help with updating the compile.yml and triggering it?

[SanftMonster]

v0.11.2 has been released in #651, please take a try to see if this issue has been fixed. Thank you!

[IntptrMax]

It works well and have a wonderful speed! Thank you!