Context Navigation

Changes between Initial Version and Version 1 of Ticket #17550

initial	v1
23	23	9) Torch warns about setting matrix multiplication floating point mode for using tensor cores with an Nvidia gpu is available. Apparently this can speed up matrix multiplications many fold. Test if this speeds up predictions without degrading prediction quality, for instance, using 16-bit float.
24	24
25		10) Profile Boltz with torch memory profiler to identify high memory use part and see if Boltz can be made more memory efficient to allow larger predictions, e.g. by switching from float32 to float16 for biggest tensors, or from assigning those big memory hog layers to the CPU even when GPU is available if the prediction is sufficiently large.
	25	10) Profile Boltz with torch memory profiler to identify high memory use part and see if Boltz can be made more memory efficient to allow larger predictions, e.g. by switching from float32 to float16 for biggest tensors, or from assigning those big memory hog layers to the CPU even when GPU is available if the prediction is sufficiently large. Ticket #17555.
26	26
27	27	11) Figure out if there are any speed optimizations for Torch / Boltz on Intel CPUs on Windows. Not too likely, but this platform is really slow.