Add integration/CMake for SYCL backend

[Jacoby1218]

At this point, given the >4GB allocation bug was fixed, if possible, I'd like to see the SYCL backend integrated into koboldcpp. While Intel GPUs are supported by Vulkan, SYCL is much faster at prompt processing (4-7x in some cases, though Vulkan is getting faster.) Even if it's not included by default with koboldcpp (much like hipBLAS) it should be supported as a backend.

[LostRuins]

Unfortunately I have no way to test it as I have not gotten SYCL to run on my device.

[Jacoby1218]

once ggerganov#5357 is done upstream it should at least build to test on non-Intel hardware, but understandable.

[tpimh]

I have an A770 16Gb, is there anything I can help with?

[ChristophHaag]

amd sycl support has been merged upstream btw. ggerganov#9658

Seems to only work with the sycl implementation in intel's oneapi sdk and not with any other sycl implementation but at least it's something.

[DarwinAnim8or]

I can confirm that the oneapi sycl implementation works, I've been using it myself on a Arc A380; I might see if I can adapt it to koboldcpp