Nikita Shulga 975bbc63db [MPS][BE] Move fmod/remainder to Metal ops (#154280) ... This accomplishes following: - Fixes correctness problem with large integer types (though probably makes it slower, but this could not be avoided if one wants to compute accurate answer) - Makes op faster for floating point types (as Metal kernel invocation is faster than creating MPSGraph) - Eliminates need for several correctness workarounds Fixes https://github.com/pytorch/pytorch/issues/154171 Pull Request resolved: https://github.com/pytorch/pytorch/pull/154280 Approved by: https://github.com/dcci ghstack dependencies: #154275, #154290		2025-05-24 01:45:33 +00:00
..
atomic.h	[MPS] Extend index_put to half precision floats (#151869)	2025-04-22 22:00:08 +00:00
common.h	[Metal] Extend typecasted op support to complex dtypes (#152504)	2025-04-30 05:32:07 +00:00
indexing.h	[BE][MPS] Pass alpha by reference (#152737)	2025-05-03 08:31:45 +00:00
random.h	[MPSInductor] Add rand support (#145705)	2025-01-27 06:07:36 +00:00
reduction_utils.h	[MPSInductor] Fix larger-than-threadgroup Welford reductions (#151152)	2025-04-12 21:44:51 +00:00
special_math.h	[MPS/inductor] Fix the approximation of polygamma for n == 0. (#152214)	2025-04-25 22:42:45 +00:00
utils.h	[MPS][BE] Move fmod/remainder to Metal ops (#154280)	2025-05-24 01:45:33 +00:00