You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
I have ready #20#219 and #56 and those seem to work well to put the processing onto the CPU but is there any way to support VPUs such as the Intel Neural Compute Stick?
The text was updated successfully, but these errors were encountered:
colemickens
pushed a commit
to colemickens/stable-diffusion
that referenced
this issue
Sep 15, 2022
Trying to Google a solution for using 6x Neural Compute Stick 2 devices in tandem with on-board Core i9-9750H graphics (24 EU, OpenCL and SyCL) and an RTX 2070 Max-Q (CUDA, OpenCL, SyCL) -- HIP was compiled as well.
I only seem to be finding guides for running OpenCL kernels on the NCS2, which is not helpful at the moment.
(zluda - which runs CUDA on Intel iGPUs, works with elderly integrated GPUs. Would be super marvelous for the VPUs to be utilized)
I have ready #20 #219 and #56 and those seem to work well to put the processing onto the CPU but is there any way to support VPUs such as the Intel Neural Compute Stick?
The text was updated successfully, but these errors were encountered: